megvii-research / fsce Goto Github PK

License: Apache License 2.0

Python 88.42% C++ 4.13% Cuda 7.46%

fsce's Introduction

FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding (CVPR 2021)

This repo contains the implementation of our state-of-the-art fewshot object detector, described in our CVPR 2021 paper, FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding. FSCE is built upon the codebase FsDet v0.1, which released by an ICML 2020 paper Frustratingly Simple Few-Shot Object Detection.

Bibtex

@inproceedings{FSCEv1,
 author = {Sun, Bo and Li, Banghuai and Cai, Shengcai and Yuan, Ye and Zhang, Chi},
 title = {FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding},
 booktitle = {Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)},
 pages    = {TBD},
 month = {June},
 year = {2021}
}

Arxiv: https://arxiv.org/abs/2103.05950

Contact

If you have any questions, please contact Bo Sun (bos [at] usc.edu) or Banghuai Li(libanghuai [at] megvii.com)

Installation

FsDet is built on Detectron2. But you don't need to build detectron2 seperately as this codebase is self-contained. You can follow the instructions below to install the dependencies and build FsDet. FSCE functionalities are implemented as classand .py scripts in FsDet which therefore requires no extra build efforts.

Dependencies

Linux with Python >= 3.6
PyTorch >= 1.3
torchvision that matches the PyTorch installation
Dependencies: pip install -r requirements.txt
pycocotools: pip install cython; pip install 'git+https://github.com/cocodataset/cocoapi.git#subdirectory=PythonAPI'
fvcore: pip install 'git+https://github.com/facebookresearch/fvcore'
OpenCV, optional, needed by demo and visualization pip install opencv-python
GCC >= 4.9

Build

python setup.py build develop  # you might need sudo

Note: you may need to rebuild FsDet after reinstalling a different build of PyTorch.

Data preparation

We adopt the same benchmarks as in FsDet, including three datasets: PASCAL VOC, COCO and LVIS.

PASCAL VOC: We use the train/val sets of PASCAL VOC 2007+2012 for training and the test set of PASCAL VOC 2007 for evaluation. We randomly split the 20 object classes into 15 base classes and 5 novel classes, and we consider 3 random splits. The splits can be found in fsdet/data/datasets/builtin_meta.py.
COCO: We use COCO 2014 without COCO minival for training and the 5,000 images in COCO minival for testing. We use the 20 object classes that are the same with PASCAL VOC as novel classes and use the rest as base classes.
LVIS: We treat the frequent and common classes as the base classes and the rare categories as the novel classes.

The datasets and data splits are built-in, simply make sure the directory structure agrees with datasets/README.md to launch the program.

The default seed that is used to report performace in research papers can be found here.

Code Structure

The code structure follows Detectron2 v0.1.* and fsdet.

configs: Configuration files (YAML) for train/test jobs.
datasets: Dataset files (see Data Preparation for more details)
fsdet
- checkpoint: Checkpoint code.
- config: Configuration code and default configurations.
- data: Dataset code.
- engine: Contains training and evaluation loops and hooks.
- evaluation: Evaluation code for different datasets.
- layers: Implementations of different layers used in models.
- modeling: Code for models, including backbones, proposal networks, and prediction heads.
  - The majority of FSCE functionality are implemtended inmodeling/roi_heads/* , modeling/contrastive_loss.py, and modeling/utils.py
  - So one can first make sure FsDet v0.1 runs smoothly, and then refer to FSCE implementations and configurations.
- solver: Scheduler and optimizer code.
- structures: Data types, such as bounding boxes and image lists.
- utils: Utility functions.
tools
- train_net.py: Training script.
- test_net.py: Testing script.
- ckpt_surgery.py: Surgery on checkpoints.
- run_experiments.py: Running experiments across many seeds.
- aggregate_seeds.py: Aggregating results from many seeds.

Train & Inference

Training

We follow the eaact training procedure of FsDet and we use random initialization for novel weights. For a full description of training procedure, see here.

1. Stage 1: Training base detector.

python tools/train_net.py --num-gpus 8 \
        --config-file configs/PASCAL_VOC/base-training/R101_FPN_base_training_split1.yml

2. Random initialize weights for novel classes.

python tools/ckpt_surgery.py \
        --src1 checkpoints/voc/faster_rcnn/faster_rcnn_R_101_FPN_base1/model_final.pth \
        --method randinit \
        --save-dir checkpoints/voc/faster_rcnn/faster_rcnn_R_101_FPN_all1

This step will create a model_surgery.pth from model_final.pth.

Don't forget the --coco and --lvisoptions when work on the COCO and LVIS datasets, see ckpt_surgery.py for all arguments details.

3. Stage 2: Fine-tune for novel data.

python tools/train_net.py --num-gpus 8 \
        --config-file configs/PASCAL_VOC/split1/10shot_CL_IoU.yml \
        --opts MODEL.WEIGHTS WEIGHTS_PATH

Where WEIGHTS_PATH points to the model_surgery.pth generated from the previous step. Or you can specify it in the configuration yml.

Evaluation

To evaluate the trained models, run

python tools/test_net.py --num-gpus 8 \
        --config-file configs/PASCAL_VOC/split1/10shot_CL_IoU.yml \
        --eval-only

Or you can specify TEST.EVAL_PERIOD in the configuation yml to evaluate during training.

Multiple Runs

For ease of training and evaluation over multiple runs, fsdet provided several helpful scripts in tools/.

You can use tools/run_experiments.py to do the training and evaluation. For example, to experiment on 30 seeds of the first split of PascalVOC on all shots, run

python tools/run_experiments.py --num-gpus 8 \
        --shots 1 2 3 5 10 --seeds 0 30 --split 1

After training and evaluation, you can use tools/aggregate_seeds.py to aggregate the results over all the seeds to obtain one set of numbers. To aggregate the 3-shot results of the above command, run

python tools/aggregate_seeds.py --shots 3 --seeds 30 --split 1 \
        --print --plot

fsce's People

Contributors

Stargazers

Watchers

Forkers

chauncy-cai ziyehu xychen9459 dallen-code qinzhengmei rongisdragon lukas018 cvlinks debapriyahazra linyanhly jy00002 yangyin2016 ggalan87 zhengye1995 trendingtechnology kuailedagongzai junhopark0314 gist-ailab frensher yanfei-qin gegalu heihuifei shijunrong amirunpri2018 jolin576 xiaodongdreams yaning76 danke1896 lnowakow harry10459 hm-w siyuanliii chuanchelin kejuzhang erica-yang dreamwish1998 qzhangli varlit woojulee24 hanwhapaullee huyanchen-hub zhn6818 yomik-js zhengsjcode im98tyx borgorg

fsce's Issues

Each file contains the images for K shots for a specific category. There may be more instances in the images than K; in these cases, we randomly sample K instances.

Hi, please tell me what does this sentence mean? I am a little confused, thanks

If there is only one category, is the algorithm applicable?

About the proposals feature cluster visualization

Hi, I wanna know what preprocessing, such as normalization, on proposals featuer should be done to visualize them using t-SNE? And can you share the code for visualization of proposals feature cluster ?

Variants about MoCo and Prototype

In your code, there are some variants based on MoCo ("eg, ContrastiveROIHeadsWithStorage") or Prototype ("eg, ContrastiveROIHeadsWithPrototype"). What is the final result (nAP) of these two variants? Will it be much lower than the optimal result reported in the paper?

confusion about datasets

you mention Expected dataset structure for Pascal VOC:VOC20{07,12}/
Annotations/
ImageSets/
JPEGImages/
where is the test set, is in these directries?

Confusion about the VOC result

Hi, In the Table 2 of the paper, you compare the average ap of mutiple runs of 10 seeds with the results given by TFA which is a average one of 30 seeds.However it is obvious that the former is anyway better than the latter according to the graph shown in TFA, So maybe this seems to be a little unresonable? Look forward to your reply.

Contrastive Proposal Encoding (CPE) Loss is not used for shot1 and 2 on the Pascal dataset？

It's nice to see the interesting work the authors are doing on Fewshot！
But from the configuration files provided with the code you can see that Shot1 and 2 did not unfreeze FPN and RPN and did not use the CPE loss proposed by the authors.

I don't know if it's because the authors forgot to release the corresponding configuration files for Shot1 and 2, or if the results reported in the paper are only fine-tuning based on TFA.

Hope the author can answer, thanks!!!

@bsun0802

Where is the file /fsdet/data/

As the title, I can't find the file /fsdet/data... I hope you can update it, thanks.

failed when building

When running the command "python setup.py build develop", I got an error--command 'gcc' failed with exit status 1. How can I fix it? Dose it means the version of gcc is not right?

Can not reproduce the split1 shot5 result

I followed the guidance of README (without any change) to pretrain a base model and then randomly initilize the novel weights, finally finetune it.But I get a best result of nap of only 58.8，there is a big gap between my result and the result given in paper.How come

And I wanna konw whether the config files shown in the repo is the same as the ones you use in your experiment

Question about training time

I cannot experiment with 8 GPUs. Can you tell me how long it takes to train in an 8-GPU environment?

How to visualize the results?

built error

I met the error: NotADirectoryError: [Errno 20] Not a directory: '/home/FSCE/fsdet/model_zoo/configs'
when I run python setup.py build develop, how can I solve it ? Waiting for your reply!

和fsdet冻结方式的不同？

我想请问下面这种冻结方式
if cfg.MODEL.BACKBONE.FREEZE:
for p in self.backbone.parameters():
p.requires_grad = False
print('froze backbone parameters')

    if cfg.MODEL.BACKBONE.FREEZE_P5:
        for connection in [self.backbone.fpn_lateral5, self.backbone.fpn_output5]:
            for p in connection.parameters():
                p.requires_grad = False
        print('frozen P5 in FPN')

是不是已经覆盖了
if freeze_at >= 1:
for p in stem.parameters():
p.requires_grad = False
stem = FrozenBatchNorm2d.convert_frozen_batchnorm(stem)
if freeze_at >= stage_idx:
for block in blocks:
block.freeze()
stages.append(blocks)
这种冻结方式？
这两种冻结方式有什么不同呢？

problem during installation

Hello, in the instruction, there is a line showing "Dependencies: pip install -r requirements.txt", but how could I find this .txt file?
When I run the setup file, the following error msg appears, do you have any clue about this?
Any suggestions will be appreciated!

(FSCE) qiuxinkuan@aa-ESC8000:/data2/qiuxinkuan/FSCE$ python setup.py build develop
running build
running build_py
running build_ext
building 'fsdet.C' extension
Emitting ninja build file /data2/qiuxinkuan/FSCE/build/temp.linux-x86_64-3.7/build.ninja...
Compiling objects...
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
[1/8] :/home/qiuxinkuan/cuda-10.1/bin/nvcc -DWITH_CUDA -I/data2/qiuxinkuan/FSCE/fsdet/layers/csrc -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/TH -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/THC -I:/home/qiuxinkuan/cuda-10.1/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/include/python3.7m -c -c /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/ROIAlign/ROIAlign_cuda.cu -o /data2/qiuxinkuan/FSCE/build/temp.linux-x86_64-3.7/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/ROIAlign/ROIAlign_cuda.o -D__CUDA_NO_HALF_OPERATORS_ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="gcc"' '-DPYBIND11_STDLIB="libstdcpp"' '-DPYBIND11_BUILD_ABI="cxxabi1011"' -DTORCH_EXTENSION_NAME=C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_61,code=sm_61 -std=c++14
**FAILED: /data2/qiuxinkuan/FSCE/build/temp.linux-x86_64-**3.7/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/ROIAlign/ROIAlign_cuda.o
:/home/qiuxinkuan/cuda-10.1/bin/nvcc -DWITH_CUDA -I/data2/qiuxinkuan/FSCE/fsdet/layers/csrc -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/TH -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/THC -I:/home/qiuxinkuan/cuda-10.1/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/include/python3.7m -c -c /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/ROIAlign/ROIAlign_cuda.cu -o /data2/qiuxinkuan/FSCE/build/temp.linux-x86_64-3.7/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/ROIAlign/ROIAlign_cuda.o -D__CUDA_NO_HALF_OPERATORS -D__CUDA_NO_HALF_CONVERSIONS -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="gcc"' '-DPYBIND11_STDLIB="libstdcpp"' '-DPYBIND11_BUILD_ABI="cxxabi1011"' -DTORCH_EXTENSION_NAME=C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_61,code=sm_61 -std=c++14
/bin/sh: 1: :/home/qiuxinkuan/cuda-10.1/bin/nvcc: not found
[2/8] :/home/qiuxinkuan/cuda-10.1/bin/nvcc -DWITH_CUDA -I/data2/qiuxinkuan/FSCE/fsdet/layers/csrc -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/TH -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/THC -I:/home/qiuxinkuan/cuda-10.1/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/include/python3.7m -c -c /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv_cuda_kernel.cu -o /data2/qiuxinkuan/FSCE/build/temp.linux-x86_64-3.7/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv_cuda_kernel.o -D__CUDA_NO_HALF_OPERATORS -D__CUDA_NO_HALF_CONVERSIONS -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="gcc"' '-DPYBIND11_STDLIB="libstdcpp"' '-DPYBIND11_BUILD_ABI="cxxabi1011"' -DTORCH_EXTENSION_NAME=C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_61,code=sm_61 -std=c++14
**FAILED: /data2/qiuxinkuan/FSCE/build/temp.linux-x86_64-**3.7/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv_cuda_kernel.o
:/home/qiuxinkuan/cuda-10.1/bin/nvcc -DWITH_CUDA -I/data2/qiuxinkuan/FSCE/fsdet/layers/csrc -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/TH -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/THC -I:/home/qiuxinkuan/cuda-10.1/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/include/python3.7m -c -c /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv_cuda_kernel.cu -o /data2/qiuxinkuan/FSCE/build/temp.linux-x86_64-3.7/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv_cuda_kernel.o -D__CUDA_NO_HALF_OPERATORS -D__CUDA_NO_HALF_CONVERSIONS -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="gcc"' '-DPYBIND11_STDLIB="libstdcpp"' '-DPYBIND11_BUILD_ABI="cxxabi1011"' -DTORCH_EXTENSION_NAME=C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_61,code=sm_61 -std=c++14
/bin/sh: 1: :/home/qiuxinkuan/cuda-10.1/bin/nvcc: not found
[3/8] :/home/qiuxinkuan/cuda-10.1/bin/nvcc -DWITH_CUDA -I/data2/qiuxinkuan/FSCE/fsdet/layers/csrc -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/TH -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/THC -I:/home/qiuxinkuan/cuda-10.1/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/include/python3.7m -c -c /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/nms_rotated/nms_rotated_cuda.cu -o /data2/qiuxinkuan/FSCE/build/temp.linux-x86_64-3.7/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/nms_rotated/nms_rotated_cuda.o -D__CUDA_NO_HALF_OPERATORS -D__CUDA_NO_HALF_CONVERSIONS -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="gcc"' '-DPYBIND11_STDLIB="libstdcpp"' '-DPYBIND11_BUILD_ABI="cxxabi1011"' -DTORCH_EXTENSION_NAME=C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_61,code=sm_61 -std=c++14
FAILED: /data2/qiuxinkuan/FSCE/build/temp.linux-x86_64-3.7/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/nms_rotated/nms_rotated_cuda.o
:/home/qiuxinkuan/cuda-10.1/bin/nvcc -DWITH_CUDA -I/data2/qiuxinkuan/FSCE/fsdet/layers/csrc -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/TH -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/THC -I:/home/qiuxinkuan/cuda-10.1/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/include/python3.7m -c -c /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/nms_rotated/nms_rotated_cuda.cu -o /data2/qiuxinkuan/FSCE/build/temp.linux-x86_64-3.7/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/nms_rotated/nms_rotated_cuda.o -D__CUDA_NO_HALF_OPERATORS -D__CUDA_NO_HALF_CONVERSIONS -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="gcc"' '-DPYBIND11_STDLIB="libstdcpp"' '-DPYBIND11_BUILD_ABI="cxxabi1011"' -DTORCH_EXTENSION_NAME=C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_61,code=sm_61 -std=c++14
/bin/sh: 1: :/home/qiuxinkuan/cuda-10.1/bin/nvcc: not found
[4/8] :/home/qiuxinkuan/cuda-10.1/bin/nvcc -DWITH_CUDA -I/data2/qiuxinkuan/FSCE/fsdet/layers/csrc -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/TH -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/THC -I:/home/qiuxinkuan/cuda-10.1/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/include/python3.7m -c -c /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv_cuda.cu -o /data2/qiuxinkuan/FSCE/build/temp.linux-x86_64-3.7/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv_cuda.o -D__CUDA_NO_HALF_OPERATORS -D__CUDA_NO_HALF_CONVERSIONS -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="gcc"' '-DPYBIND11_STDLIB="libstdcpp"' '-DPYBIND11_BUILD_ABI="cxxabi1011"' -DTORCH_EXTENSION_NAME=C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_61,code=sm_61 -std=c++14
**FAILED: /data2/qiuxinkuan/FSCE/build/temp.linux-x86_64-**3.7/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv_cuda.o
:/home/qiuxinkuan/cuda-10.1/bin/nvcc -DWITH_CUDA -I/data2/qiuxinkuan/FSCE/fsdet/layers/csrc -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/TH -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/THC -I:/home/qiuxinkuan/cuda-10.1/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/include/python3.7m -c -c /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv_cuda.cu -o /data2/qiuxinkuan/FSCE/build/temp.linux-x86_64-3.7/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv_cuda.o -D__CUDA_NO_HALF_OPERATORS -D__CUDA_NO_HALF_CONVERSIONS -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="gcc"' '-DPYBIND11_STDLIB="libstdcpp"' '-DPYBIND11_BUILD_ABI="cxxabi1011"' -DTORCH_EXTENSION_NAME=C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_61,code=sm_61 -std=c++14
/bin/sh: 1: :/home/qiuxinkuan/cuda-10.1/bin/nvcc: not found
[5/8] :/home/qiuxinkuan/cuda-10.1/bin/nvcc -DWITH_CUDA -I/data2/qiuxinkuan/FSCE/fsdet/layers/csrc -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/TH -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/THC -I:/home/qiuxinkuan/cuda-10.1/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/include/python3.7m -c -c /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/box_iou_rotated/box_iou_rotated_cuda.cu -o /data2/qiuxinkuan/FSCE/build/temp.linux-x86_64-3.7/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/box_iou_rotated/box_iou_rotated_cuda.o -D__CUDA_NO_HALF_OPERATORS -D__CUDA_NO_HALF_CONVERSIONS -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="gcc"' '-DPYBIND11_STDLIB="libstdcpp"' '-DPYBIND11_BUILD_ABI="cxxabi1011"' -DTORCH_EXTENSION_NAME=C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_61,code=sm_61 -std=c++14
FAILED: /data2/qiuxinkuan/FSCE/build/temp.linux-x86_64-3.7/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/box_iou_rotated/box_iou_rotated_cuda.o
:/home/qiuxinkuan/cuda-10.1/bin/nvcc -DWITH_CUDA -I/data2/qiuxinkuan/FSCE/fsdet/layers/csrc -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/TH -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/THC -I:/home/qiuxinkuan/cuda-10.1/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/include/python3.7m -c -c /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/box_iou_rotated/box_iou_rotated_cuda.cu -o /data2/qiuxinkuan/FSCE/build/temp.linux-x86_64-3.7/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/box_iou_rotated/box_iou_rotated_cuda.o -D__CUDA_NO_HALF_OPERATORS -D__CUDA_NO_HALF_CONVERSIONS -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="gcc"' '-DPYBIND11_STDLIB="libstdcpp"' '-DPYBIND11_BUILD_ABI="cxxabi1011"' -DTORCH_EXTENSION_NAME=C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_61,code=sm_61 -std=c++14
/bin/sh: 1: :/home/qiuxinkuan/cuda-10.1/bin/nvcc: not found
[6/8] :/home/qiuxinkuan/cuda-10.1/bin/nvcc -DWITH_CUDA -I/data2/qiuxinkuan/FSCE/fsdet/layers/csrc -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/TH -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/THC -I:/home/qiuxinkuan/cuda-10.1/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/include/python3.7m -c -c /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/cuda_version.cu -o /data2/qiuxinkuan/FSCE/build/temp.linux-x86_64-3.7/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/cuda_version.o -D__CUDA_NO_HALF_OPERATORS -D__CUDA_NO_HALF_CONVERSIONS -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="gcc"' '-DPYBIND11_STDLIB="libstdcpp"' '-DPYBIND11_BUILD_ABI="cxxabi1011"' -DTORCH_EXTENSION_NAME=C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_61,code=sm_61 -std=c++14
FAILED: /data2/qiuxinkuan/FSCE/build/temp.linux-x86_64-3.7/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/cuda_version.o
:/home/qiuxinkuan/cuda-10.1/bin/nvcc -DWITH_CUDA -I/data2/qiuxinkuan/FSCE/fsdet/layers/csrc -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/TH -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/THC -I:/home/qiuxinkuan/cuda-10.1/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/include/python3.7m -c -c /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/cuda_version.cu -o /data2/qiuxinkuan/FSCE/build/temp.linux-x86_64-3.7/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/cuda_version.o -D__CUDA_NO_HALF_OPERATORS -D__CUDA_NO_HALF_CONVERSIONS -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="gcc"' '-DPYBIND11_STDLIB="libstdcpp"' '-DPYBIND11_BUILD_ABI="cxxabi1011"' -DTORCH_EXTENSION_NAME=C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_61,code=sm_61 -std=c++14
/bin/sh: 1: :/home/qiuxinkuan/cuda-10.1/bin/nvcc: not found
[7/8] :/home/qiuxinkuan/cuda-10.1/bin/nvcc -DWITH_CUDA -I/data2/qiuxinkuan/FSCE/fsdet/layers/csrc -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/TH -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/THC -I:/home/qiuxinkuan/cuda-10.1/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/include/python3.7m -c -c /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/ROIAlignRotated/ROIAlignRotated_cuda.cu -o /data2/qiuxinkuan/FSCE/build/temp.linux-x86_64-3.7/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/ROIAlignRotated/ROIAlignRotated_cuda.o -D__CUDA_NO_HALF_OPERATORS -D__CUDA_NO_HALF_CONVERSIONS -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="gcc"' '-DPYBIND11_STDLIB="libstdcpp"' '-DPYBIND11_BUILD_ABI="cxxabi1011"' -DTORCH_EXTENSION_NAME=C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_61,code=sm_61 -std=c++14
FAILED: /data2/qiuxinkuan/FSCE/build/temp.linux-x86_64-3.7/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/ROIAlignRotated/ROIAlignRotated_cuda.o
:/home/qiuxinkuan/cuda-10.1/bin/nvcc -DWITH_CUDA -I/data2/qiuxinkuan/FSCE/fsdet/layers/csrc -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/TH -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/THC -I:/home/qiuxinkuan/cuda-10.1/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/include/python3.7m -c -c /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/ROIAlignRotated/ROIAlignRotated_cuda.cu -o /data2/qiuxinkuan/FSCE/build/temp.linux-x86_64-3.7/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/ROIAlignRotated/ROIAlignRotated_cuda.o -D__CUDA_NO_HALF_OPERATORS -D__CUDA_NO_HALF_CONVERSIONS -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -DCUDA_HAS_FP16=1 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_61,code=sm_61 -std=c++14
/bin/sh: 1: :/home/qiuxinkuan/cuda-10.1/bin/nvcc: not found
[8/8] c++ -MMD -MF /data2/qiuxinkuan/FSCE/build/temp.linux-x86_64-3.7/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.o.d -pthread -B /home/qiuxinkuan/anaconda3/envs/FSCE/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_CUDA -I/data2/qiuxinkuan/FSCE/fsdet/layers/csrc -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/TH -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/THC -I:/home/qiuxinkuan/cuda-10.1/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/include/python3.7m -c -c /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp -o /data2/qiuxinkuan/FSCE/build/temp.linux-x86_64-3.7/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.o -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++14
FAILED: /data2/qiuxinkuan/FSCE/build/temp.linux-x86_64-3.7/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.o
c++ -MMD -MF /data2/qiuxinkuan/FSCE/build/temp.linux-x86_64-3.7/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.o.d -pthread -B /home/qiuxinkuan/anaconda3/envs/FSCE/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_CUDA -I/data2/qiuxinkuan/FSCE/fsdet/layers/csrc -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/TH -I/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/THC -I:/home/qiuxinkuan/cuda-10.1/include -I/home/qiuxinkuan/anaconda3/envs/FSCE/include/python3.7m -c -c /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp -o /data2/qiuxinkuan/FSCE/build/temp.linux-x86_64-3.7/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.o -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=_C -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++14
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
In file included from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Parallel.h:149:0,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/utils.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/nn/cloneable.h:5,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/nn.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:12,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/extension.h:4,
from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:3:
/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/ParallelOpenMP.h:84:0: warning: ignoring #pragma omp parallel [-Wunknown-pragmas]
#pragma omp parallel for if ((end - begin) >= grain_size)
^
In file included from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:4:0:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/ROIAlign/ROIAlign.h: In function ‘at::Tensor fsdet::ROIAlign_forward(const at::Tensor&, const at::Tensor&, float, int, int, int, bool)’:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/ROIAlign/ROIAlign.h:62:18: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
if (input.type().is_cuda()) {
^
In file included from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:3:0,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/ATen.h:9,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/extension.h:4,
from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:3:
/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:277:30: note: declared here
DeprecatedTypeProperties & type() const {
^
In file included from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:4:0:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/ROIAlign/ROIAlign.h: In function ‘at::Tensor fsdet::ROIAlign_backward(const at::Tensor&, const at::Tensor&, float, int, int, int, int, int, int, int, bool)’:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/ROIAlign/ROIAlign.h:98:17: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
if (grad.type().is_cuda()) {
^
In file included from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:3:0,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/ATen.h:9,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/extension.h:4,
from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:3:
/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:277:30: note: declared here
DeprecatedTypeProperties & type() const {
^
In file included from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:5:0:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/ROIAlignRotated/ROIAlignRotated.h: In function ‘at::Tensor fsdet::ROIAlignRotated_forward(const at::Tensor&, const at::Tensor&, float, int, int, int)’:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/ROIAlignRotated/ROIAlignRotated.h:57:18: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
if (input.type().is_cuda()) {
^
In file included from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:3:0,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/ATen.h:9,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/extension.h:4,
from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:3:
/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:277:30: note: declared here
DeprecatedTypeProperties & type() const {
^
In file included from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:5:0:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/ROIAlignRotated/ROIAlignRotated.h: In function ‘at::Tensor fsdet::ROIAlignRotated_backward(const at::Tensor&, const at::Tensor&, float, int, int, int, int, int, int, int)’:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/ROIAlignRotated/ROIAlignRotated.h:85:17: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
if (grad.type().is_cuda()) {
^
In file included from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:3:0,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/ATen.h:9,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/extension.h:4,
from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:3:
/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:277:30: note: declared here
DeprecatedTypeProperties & type() const {
^
In file included from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:7:0:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv.h: In function ‘int fsdet::deform_conv_forward(at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, int, int, int, int, int, int, int, int, int, int, int)’:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv.h:134:18: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
if (input.type().is_cuda()) {
^
In file included from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:3:0,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/ATen.h:9,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/extension.h:4,
from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:3:
/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:277:30: note: declared here
DeprecatedTypeProperties & type() const {
^
In file included from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:7:0:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv.h:136:26: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
AT_CHECK(weight.type().is_cuda(), "weight tensor is not on GPU!");
^
In file included from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:3:0,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/ATen.h:9,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/extension.h:4,
from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:3:
/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:277:30: note: declared here
DeprecatedTypeProperties & type() const {
^
In file included from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:7:0:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv.h:136:69: error: ‘AT_CHECK’ was not declared in this scope
AT_CHECK(weight.type().is_cuda(), "weight tensor is not on GPU!");
^
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv.h:137:26: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
AT_CHECK(offset.type().is_cuda(), "offset tensor is not on GPU!");
^
In file included from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:3:0,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/ATen.h:9,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/extension.h:4,
from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:3:
/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:277:30: note: declared here
DeprecatedTypeProperties & type() const {
^
In file included from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:7:0:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv.h: In function ‘int fsdet::deform_conv_backward_input(at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, int, int, int, int, int, int, int, int, int, int, int)’:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv.h:182:23: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
if (gradOutput.type().is_cuda()) {
^
In file included from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:3:0,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/ATen.h:9,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/extension.h:4,
from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:3:
/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:277:30: note: declared here
DeprecatedTypeProperties & type() const {
^
In file included from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:7:0:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv.h:184:25: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
AT_CHECK(input.type().is_cuda(), "input tensor is not on GPU!");
^
In file included from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:3:0,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/ATen.h:9,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/extension.h:4,
from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:3:
/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:277:30: note: declared here
DeprecatedTypeProperties & type() const {
^
In file included from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:7:0:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv.h:184:67: error: ‘AT_CHECK’ was not declared in this scope
AT_CHECK(input.type().is_cuda(), "input tensor is not on GPU!");
^
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv.h:185:26: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
AT_CHECK(weight.type().is_cuda(), "weight tensor is not on GPU!");
^
In file included from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:3:0,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/ATen.h:9,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/extension.h:4,
from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:3:
/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:277:30: note: declared here
DeprecatedTypeProperties & type() const {
^
In file included from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:7:0:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv.h:186:26: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
AT_CHECK(offset.type().is_cuda(), "offset tensor is not on GPU!");
^
In file included from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:3:0,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/ATen.h:9,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/extension.h:4,
from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:3:
/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:277:30: note: declared here
DeprecatedTypeProperties & type() const {
^
In file included from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:7:0:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv.h: In function ‘int fsdet::deform_conv_backward_filter(at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, int, int, int, int, int, int, int, int, int, int, float, int)’:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv.h:232:23: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
if (gradOutput.type().is_cuda()) {
^
In file included from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:3:0,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/ATen.h:9,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/extension.h:4,
from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:3:
/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:277:30: note: declared here
DeprecatedTypeProperties & type() const {
^
In file included from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:7:0:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv.h:234:25: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
AT_CHECK(input.type().is_cuda(), "input tensor is not on GPU!");
^
In file included from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:3:0,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/ATen.h:9,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/extension.h:4,
from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:3:
/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:277:30: note: declared here
DeprecatedTypeProperties & type() const {
^
In file included from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:7:0:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv.h:234:67: error: ‘AT_CHECK’ was not declared in this scope
AT_CHECK(input.type().is_cuda(), "input tensor is not on GPU!");
^
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv.h:235:26: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
AT_CHECK(offset.type().is_cuda(), "offset tensor is not on GPU!");
^
In file included from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:3:0,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/ATen.h:9,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/extension.h:4,
from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:3:
/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:277:30: note: declared here
DeprecatedTypeProperties & type() const {
^
In file included from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:7:0:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv.h: In function ‘void fsdet::modulated_deform_conv_forward(at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, int, int, int, int, int, int, int, int, int, int, bool)’:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv.h:282:18: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
if (input.type().is_cuda()) {
^
In file included from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:3:0,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/ATen.h:9,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/extension.h:4,
from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:3:
/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:277:30: note: declared here
DeprecatedTypeProperties & type() const {
^
In file included from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:7:0:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv.h:284:26: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
AT_CHECK(weight.type().is_cuda(), "weight tensor is not on GPU!");
^
In file included from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:3:0,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/ATen.h:9,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/extension.h:4,
from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:3:
/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:277:30: note: declared here
DeprecatedTypeProperties & type() const {
^
In file included from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:7:0:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv.h:284:69: error: ‘AT_CHECK’ was not declared in this scope
AT_CHECK(weight.type().is_cuda(), "weight tensor is not on GPU!");
^
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv.h:285:24: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
AT_CHECK(bias.type().is_cuda(), "bias tensor is not on GPU!");
^
In file included from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:3:0,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/ATen.h:9,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/extension.h:4,
from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:3:
/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:277:30: note: declared here
DeprecatedTypeProperties & type() const {
^
In file included from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:7:0:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv.h:286:26: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
AT_CHECK(offset.type().is_cuda(), "offset tensor is not on GPU!");
^
In file included from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:3:0,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/ATen.h:9,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/extension.h:4,
from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:3:
/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:277:30: note: declared here
DeprecatedTypeProperties & type() const {
^
In file included from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:7:0:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv.h: In function ‘void fsdet::modulated_deform_conv_backward(at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, int, int, int, int, int, int, int, int, int, int, bool)’:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv.h:339:24: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
if (grad_output.type().is_cuda()) {
^
In file included from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:3:0,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/ATen.h:9,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/extension.h:4,
from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:3:
/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:277:30: note: declared here
DeprecatedTypeProperties & type() const {
^
In file included from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:7:0:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv.h:341:25: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
AT_CHECK(input.type().is_cuda(), "input tensor is not on GPU!");
^
In file included from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:3:0,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/ATen.h:9,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/extension.h:4,
from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:3:
/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:277:30: note: declared here
DeprecatedTypeProperties & type() const {
^
In file included from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:7:0:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv.h:341:67: error: ‘AT_CHECK’ was not declared in this scope
AT_CHECK(input.type().is_cuda(), "input tensor is not on GPU!");
^
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv.h:342:26: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
AT_CHECK(weight.type().is_cuda(), "weight tensor is not on GPU!");
^
In file included from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:3:0,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/ATen.h:9,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/extension.h:4,
from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:3:
/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:277:30: note: declared here
DeprecatedTypeProperties & type() const {
^
In file included from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:7:0:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv.h:343:24: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
AT_CHECK(bias.type().is_cuda(), "bias tensor is not on GPU!");
^
In file included from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:3:0,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/ATen.h:9,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/extension.h:4,
from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:3:
/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:277:30: note: declared here
DeprecatedTypeProperties & type() const {
^
In file included from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:7:0:
/data2/qiuxinkuan/FSCE/fsdet/layers/csrc/deformable/deform_conv.h:344:26: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
AT_CHECK(offset.type().is_cuda(), "offset tensor is not on GPU!");
^
In file included from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:3:0,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/ATen.h:9,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
from /home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/torch/extension.h:4,
from /data2/qiuxinkuan/FSCE/fsdet/layers/csrc/vision.cpp:3:
/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:277:30: note: declared here
DeprecatedTypeProperties & type() const {
^
ninja: build stopped: subcommand failed.
Traceback (most recent call last):
File "/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1539, in _run_ninja_build
env=env)
File "/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/subprocess.py", line 512, in run
output=stdout, stderr=stderr)
subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "setup.py", line 114, in
cmdclass={"build_ext": torch.utils.cpp_extension.BuildExtension},
File "/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/setuptools/init.py", line 153, in setup
return distutils.core.setup(**attrs)
File "/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/distutils/core.py", line 148, in setup
dist.run_commands()
File "/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/distutils/dist.py", line 966, in run_commands
self.run_command(cmd)
File "/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/distutils/dist.py", line 985, in run_command
cmd_obj.run()
File "/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/distutils/command/build.py", line 135, in run
self.run_command(cmd_name)
File "/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/distutils/cmd.py", line 313, in run_command
self.distribution.run_command(command)
File "/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/distutils/dist.py", line 985, in run_command
cmd_obj.run()
File "/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/setuptools/command/build_ext.py", line 79, in run
_build_ext.run(self)
File "/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/Cython/Distutils/old_build_ext.py", line 186, in run
_build_ext.build_ext.run(self)
File "/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/distutils/command/build_ext.py", line 340, in run
self.build_extensions()
File "/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 670, in build_extensions
build_ext.build_extensions(self)
File "/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/Cython/Distutils/old_build_ext.py", line 195, in build_extensions
_build_ext.build_ext.build_extensions(self)
File "/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/distutils/command/build_ext.py", line 449, in build_extensions
self._build_extensions_serial()
File "/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/distutils/command/build_ext.py", line 474, in _build_extensions_serial
self.build_extension(ext)
File "/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/setuptools/command/build_ext.py", line 196, in build_extension
_build_ext.build_extension(self, ext)
File "/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/distutils/command/build_ext.py", line 534, in build_extension
depends=ext.depends)
File "/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 500, in unix_wrap_ninja_compile
with_cuda=with_cuda)
File "/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1255, in _write_ninja_file_and_compile_objects
error_prefix='Error compiling objects for extension')
File "/home/qiuxinkuan/anaconda3/envs/FSCE/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1555, in _run_ninja_build
raise RuntimeError(message) from e
RuntimeError: Error compiling objects for extension

_C.roi_align_forward raises a "RuntimeError: Not compiled with GPU support"

I'm sure my pytorch is consistent with the cuda version 11.1 and I've already built fsdet with "python setup.py build develop". But from file "fsdet\layers\roi_align.py", the "_C.roi_align_forward" method raises a "RuntimeError: Not compiled with GPU support". What can be the cause? I tried to run demo in detectron2 but it doesn't raise such error.

Confusion about the split of test set(minival 5000)

I found that you give a split of minival set which is not consistent with the original split of official set.Why do u do like this,thank u .

batch_size

Thank for your amazing code.
The batch_size of comparative study is very large(eg.simclr'batch_size has about the hundreds), why your experiment batch_size equal to 16 can be carried out? Does the contrastive branch compare the proposals produced the RPN instead of the samples(different from Contrastive Learning)?

AssertionError: get_event_storage() has to be called inside a 'with EventStorage(...)' context!

when evaluating the trained models...
please tell me how to solve it，thanks！

bug of test_net.py

AssertionError: get_event_storage() has to be called inside a 'with EventStorage(...)' context!

ImportError: cannot import name '_C' from 'fsdet'

Thanks for your great projects and Thanks for share the code of your great work!
I have done all the installations shown on README but still, I get his error message whenever I try to do the train_net.py:
Importerror: cannot import name '_C' from 'fsdet'
can you give me any advice?thanks very much.

Exception: process 0 terminated with signal SIGSEGV

Here are the details.

(FSCE) [wangyufei@node03 FSCE]$ CUDA_VISIBLE_DEVICES=8,9 python tools/train_net.py --num-gpus 2 --config-file configs/PASCAL_VOC/base-training/R101_FPN_base_training_split1.yml
Command Line Args: Namespace(config_file='configs/PASCAL_VOC/base-training/R101_FPN_base_training_split1.yml', dist_url='tcp://127.0.0.1:50363', end_iter=-1, eval_all=False, eval_during_train=False, eval_iter=-1, eval_only=False, machine_rank=0, num_gpus=2, num_machines=1, opts=[], resume=False, start_iter=-1)
[09/13 20:20:43 fsdet]: Rank of current process: 0. World size: 2
[09/13 20:20:43 fsdet]: Command line arguments: Namespace(config_file='configs/PASCAL_VOC/base-training/R101_FPN_base_training_split1.yml', dist_url='tcp://127.0.0.1:50363', end_iter=-1, eval_all=False, eval_during_train=False, eval_iter=-1, eval_only=False, machine_rank=0, num_gpus=2, num_machines=1, opts=[], resume=False, start_iter=-1)
[09/13 20:20:43 fsdet]: Contents of args.config_file=configs/PASCAL_VOC/base-training/R101_FPN_base_training_split1.yml:
BASE: "../../Base-RCNN-FPN.yaml"
MODEL:
WEIGHTS: "checkpoints/pretrained_model/R-101.pkl"
MASK_ON: False
RESNETS:
DEPTH: 101
ROI_HEADS:
NUM_CLASSES: 15
INPUT:
MIN_SIZE_TRAIN: (480, 512, 544, 576, 608, 640, 672, 704, 736, 768, 800)
MIN_SIZE_TEST: 800
DATASETS:
TRAIN: ('voc_2007_trainval_base1', 'voc_2012_trainval_base1')
TEST: ('voc_2007_test_base1',)
SOLVER:
STEPS: (12000, 16000)
MAX_ITER: 18000 # 17.4 epochs
WARMUP_ITERS: 100
OUTPUT_DIR: "checkpoints/voc/faster_rcnn/faster_rcnn_R_101_FPN_base1"

[09/13 20:20:43 fsdet]: Full config saved to /home/wangyufei/Code/FSCE/checkpoints/voc/faster_rcnn/faster_rcnn_R_101_FPN_base1/config.yaml
[09/13 20:20:43 fsdet.utils.env]: Using a generated random seed 43966721
frozen resnet backbone stage 2 (this froze ResNet but not FPN, frozen backbone in rcnn.py will overwrite this)
frozen resnet backbone stage 2 (this froze ResNet but not FPN, frozen backbone in rcnn.py will overwrite this)
-------- Using Roi Head: StandardROIHeads---------

-------- Using Roi Head: StandardROIHeads---------

[09/13 20:22:41 fsdet.data.build]: Removed 1920 images with no usable annotations. 14631 images left.
[09/13 20:22:41 fsdet.data.build]: Distribution of training instances among all 15 categories:

category	#instances	category	#instances	category	#instances
aeroplane	1285	bicycle	1208	boat	1397
bottle	2116	car	4008	cat	1616
chair	4338	diningtable	1057	dog	2079
horse	1156	person	15576	pottedplant	1724
sheep	1347	train	984	tvmonitor	1193

total	41084

[09/13 20:22:41 fsdet.data.detection_utils]: TransformGens used in training: [ResizeShortestEdge(short_edge_length=(480, 512, 544, 576, 608, 640, 672, 704, 736, 768, 800), max_size=1333, sample_style='choice'), RandomFlip()]
[09/13 20:22:41 fsdet.data.build]: Using training sampler TrainingSampler
[09/13 20:23:14 fvcore.common.checkpoint]: Loading checkpoint from checkpoints/pretrained_model/R-101.pkl
[09/13 20:23:14 fsdet.checkpoint.c2_model_loading]: Remapping C2 weights ......
[09/13 20:23:15 fsdet.checkpoint.c2_model_loading]: Some model parameters are not in the checkpoint:
backbone.fpn_lateral2.{bias, weight}
backbone.fpn_lateral3.{bias, weight}
backbone.fpn_lateral4.{bias, weight}
backbone.fpn_lateral5.{bias, weight}
backbone.fpn_output2.{bias, weight}
backbone.fpn_output3.{bias, weight}
backbone.fpn_output4.{bias, weight}
backbone.fpn_output5.{bias, weight}
proposal_generator.anchor_generator.cell_anchors.{0, 1, 2, 3, 4}
proposal_generator.rpn_head.anchor_deltas.{bias, weight}
proposal_generator.rpn_head.conv.{bias, weight}
proposal_generator.rpn_head.objectness_logits.{bias, weight}
roi_heads.box_head.fc1.{bias, weight}
roi_heads.box_head.fc2.{bias, weight}
roi_heads.box_predictor.bbox_pred.{bias, weight}
roi_heads.box_predictor.cls_score.{bias, weight}
[09/13 20:23:15 fsdet.checkpoint.c2_model_loading]: The checkpoint contains parameters not used by the model:
fc1000_b
fc1000_w
[09/13 20:23:15 fsdet.engine.train_loop]: Starting training from iteration 0
/home/wangyufei/anaconda3/envs/FSCE/lib/python3.6/multiprocessing/semaphore_tracker.py:143: UserWarning: semaphore_tracker: There appear to be 20 leaked semaphores to clean up at shutdown
len(cache))
Traceback (most recent call last):
File "tools/train_net.py", line 130, in
args=(args,),
File "/home/wangyufei/Code/FSCE/fsdet/engine/launch.py", line 49, in launch
daemon=False,
File "/home/wangyufei/anaconda3/envs/FSCE/lib/python3.6/site-packages/torch/multiprocessing/spawn.py", line 171, in spawn
while not spawn_context.join():
File "/home/wangyufei/anaconda3/envs/FSCE/lib/python3.6/site-packages/torch/multiprocessing/spawn.py", line 107, in join
(error_index, name)
Exception: process 0 terminated with signal SIGSEGV
(FSCE) [wangyufei@node03 FSCE]$ /home/wangyufei/anaconda3/envs/FSCE/lib/python3.6/multiprocessing/semaphore_tracker.py:143: UserWarning: semaphore_tracker: There appear to be 20 leaked semaphores to clean up at shutdown
len(cache))

(FSCE) [wangyufei@node03 FSCE]$

Error about annotation path when fine-tuning.

Dear author, thanks for your great work. I successfully train the pertained model, but when I fine-tuning, it reports such error:

FileNotFoundError: [Errno 2] No such file or directory: 'datasets/vocsplit/box_10shot_aeroplane_train.txt'.

I have generate the shots by running python datasets/prepare_voc_few_shot.py.

能否共享一下t-SNE的代码?并分享一下如何使用。感谢

AssertionError: Checkpoint detectron2://ImageNetPretrained/MSRA/R-101.pkl not found!

python tools/train_net.py --num-gpus 8
--config-file configs/PASCAL_VOC/base-training/R101_FPN_base_training_split1.yml

AssertionError: Box regression deltas become infinite or NaN!

I meet this exception when I run the command “CUDA_VISIBLE_DEVICES=0,1 python3 -m tools.train_net --num-gpus 2 --config-file /home/sjk/ZJX/FSCE/configs/COCO/R-101/base_training.yml” ，the IMS_PER_BATCH is set to 32 BASE_LR is set to 0.02. All discriptions are :
Traceback (most recent call last):
File "/home/sjk/anaconda3/envs/py36/lib/python3.6/runpy.py", line 193, in _run_module_as_main
"main", mod_spec)
File "/home/sjk/anaconda3/envs/py36/lib/python3.6/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/home/sjk/ZJX/FSCE/tools/train_net.py", line 132, in
args=(args,),
File "/home/sjk/ZJX/FSCE/fsdet/engine/launch.py", line 49, in launch
daemon=False,
File "/home/sjk/anaconda3/envs/py36/lib/python3.6/site-packages/torch/multiprocessing/spawn.py", line 230, in spawn
return start_processes(fn, args, nprocs, join, daemon, start_method='spawn')
File "/home/sjk/anaconda3/envs/py36/lib/python3.6/site-packages/torch/multiprocessing/spawn.py", line 188, in start_processes
while not context.join():
File "/home/sjk/anaconda3/envs/py36/lib/python3.6/site-packages/torch/multiprocessing/spawn.py", line 150, in join
raise ProcessRaisedException(msg, error_index, failed_process.pid)
torch.multiprocessing.spawn.ProcessRaisedException:

-- Process 1 terminated with the following error:
Traceback (most recent call last):
File "/home/sjk/anaconda3/envs/py36/lib/python3.6/site-packages/torch/multiprocessing/spawn.py", line 59, in _wrap
fn(i, *args)
File "/home/sjk/ZJX/FSCE/fsdet/engine/launch.py", line 84, in _distributed_worker
main_func(*args)
File "/home/sjk/ZJX/FSCE/tools/train_net.py", line 119, in main
return trainer.train()
File "/home/sjk/ZJX/FSCE/fsdet/engine/defaults.py", line 397, in train
super().train(self.start_iter, self.max_iter)
File "/home/sjk/ZJX/FSCE/fsdet/engine/train_loop.py", line 132, in train
self.run_step()
File "/home/sjk/ZJX/FSCE/fsdet/engine/train_loop.py", line 212, in run_step
loss_dict = self.model(data)
File "/home/sjk/anaconda3/envs/py36/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/home/sjk/anaconda3/envs/py36/lib/python3.6/site-packages/torch/nn/parallel/distributed.py", line 799, in forward
output = self.module(*inputs[0], **kwargs[0])
File "/home/sjk/anaconda3/envs/py36/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/home/sjk/ZJX/FSCE/fsdet/modeling/meta_arch/rcnn.py", line 148, in forward
proposals, proposal_losses = self.proposal_generator(images, features, gt_instances)
File "/home/sjk/anaconda3/envs/py36/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/home/sjk/ZJX/FSCE/fsdet/modeling/proposal_generator/rpn.py", line 176, in forward
outputs.predict_proposals(), # transform anchors to proposals by applying delta
File "/home/sjk/ZJX/FSCE/fsdet/modeling/proposal_generator/rpn_outputs.py", line 419, in predict_proposals
pred_anchor_deltas_i, anchors_i.tensor
File "/home/sjk/ZJX/FSCE/fsdet/modeling/box_regression.py", line 79, in apply_deltas
assert torch.isfinite(deltas).all().item(), "Box regression deltas become infinite or NaN!"
AssertionError: Box regression deltas become infinite or NaN!

model_reset_combine、model_reset_remove、model_reset_surgery

model_reset_combine、model_reset_remove、model_reset_surgery
请问一下大家，这几个pth有什么区别？

Unable to reproduce the results on MS COCO datasets

Dear author, I tried to reproduce the results on MS COCO using the default config and base model from http://dl.yf.io/fs-det/models/coco/base_model/model_final.pth, but got average AP 10.460 on 10 seeds, could you please provide the model_final.pth you trained? Thank you very much!

Where is the directory /fsdet/data/？

hi, I don't find the directory /fsdet/data/. I try using the files in directory /fsdet/data of https://github.com/ucbdrive/few-shot-object-detection, but it occurs error.

Questions about COCO experiments

I notice that in fine-tune stage, the COCO dataset only have one instance per image, despite of there may be number of potential instances, like some image contained chairs, and these instances without annotations would be treated as False Positive in this stage. Does it make sense?
In configs/COCO/R-101/10shot_baseline.yml, there have no config about "ContrastiveROIHeads", which was set in PACSCAL_VOC/split*/*shot_CL_IoU.yml. But I use this coco baseline achieve 11.6 nAP in 10-shot coco setting, and when I add config about CL in COCO config file it only achieve 10.16nAP. Whether I misunderstand something important?
Waiting for your response. Thanks.

How to calculate the novel class AP in base training

Thanks for your code, i'm confused with the results reported in Table 4 in the paper.
As is suggested, when doing the base training using Baseline-FPN, the base AP50 on 5 shot is 67.9 and the novel AP50 is 49.6. I wonder how it is evaluated.
I run this command python tools/train_net.py --num-gpus 2 --config-file configs/PASCAL_VOC/base_training/R101_FPN_base_training_split1.yaml

The base AP50 is 77.458. I change the DATASETS.TEST in config file to (voc_2007_test_all1) to see the performance on novel class. However, it is 0.

Please explain it, thanks.

Dear auther: can you share the T-SNE code?

Code about 'double the maximum number of proposals kept after NMS '

Thanks for your great work and source code ：）
I am confused about where the code refers to 'double the maximum number of proposals kept after NMS'.
The default configuration of _C.MODEL.RPN.POST_NMS_TOPK_TRAIN is 2000, so in my view, FSCE should set _C.MODEL.RPN.POST_NMS_TOPK_TRAIN as 4000.
However, for example, in FSCE/fsdet/config/defaults.py:

MODEL:
  RPN:
    POST_NMS_TOPK_TRAIN: 2000

am I wrong?
I would be grateful if you could help me :)

changing MODEL.BACKBONE.FREEZE_AT causes an error

Thanks for sharing your work!

I am doing some experiments with your code, and found that if I change the number of frozen layers by changing MODEL.BACKBONE.FREEZE_AT (default is 5, and I tried 0~4), then I get the following error:

{MY_WORKSPACE}/FSCE/fsdet/layers/deform_conv.py", line 114, in backward
    _C.deform_conv_backward_filter(
RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.

Could you help me to resolve this?

CPE loss is not used for MS COCO dataset?

Thanks for the great work you have done on few-shot detection!
From the config file you provided, I found that you didn't use CPE loss on MS COCO dataset. Does it mean that FSCE is just a strong baseline on MS COCO dataset?
Besides, I can't reproduce the result on MS COCO dataset, I got 11.59 (just on seed 0) while in paper the result is 11.9.
I used the base train checkpoint from http://dl.yf.io/fs-det/models/coco/base_model/model_final.pth. Could you please check the config file? Thank you!

Inconsistent setting of shot 1, 2 and 3, 5, 10

Dear author, I like your project very much. But I find that there exist inconsistent setting between shot1, 2 and 3, 5, 10, for examples,

In split1, shot1, pascal voc, FPN and RPN are frozen,
https://github.com/MegviiDetection/FSCE/blob/ad6dbd06ceb1473ba6f1c1709e1365dfb4161e2f/configs/PASCAL_VOC/split1/1shot_baseline.yml#L9-L16

But in split 1, shot3, pascal voc, FPN and RPN are unfrozen,
https://github.com/MegviiDetection/FSCE/blob/ad6dbd06ceb1473ba6f1c1709e1365dfb4161e2f/configs/PASCAL_VOC/split1/3shot_CL_IoU.yml#L9-L16.

Besides, in split1, shot1, pascal voc, test aug are disabled,
https://github.com/MegviiDetection/FSCE/blob/ad6dbd06ceb1473ba6f1c1709e1365dfb4161e2f/configs/PASCAL_VOC/split1/1shot_baseline.yml#L44-L45

However in split1, shot3, pascal voc, test aug are enabled,
https://github.com/MegviiDetection/FSCE/blob/ad6dbd06ceb1473ba6f1c1709e1365dfb4161e2f/configs/PASCAL_VOC/split1/3shot_CL_IoU.yml#L55-L58

I am really puzzled about that. Could you explain it to me? Thanks in advance!

Where is the requirement.txt?

I can't find where is the requirement.txt.
And I meet a problem about build fsdet in Windows.

Could you help me about this problem?

Training Error

Dear authors,

When I run your code, there is an error. The version of pytorch is 1.4.0 + 0.5.0 torchvision. Could you give me some advice? Thank you.

Exception: process 0 terminated with signal SIGSEGV

Here are the details.

-------- Using Roi Head: StandardROIHeads---------

[09/13 20:22:41 fsdet.data.build]: Removed 1920 images with no usable annotations. 14631 images left.
[09/13 20:22:41 fsdet.data.build]: Distribution of training instances among all 15 categories:

category	#instances	category	#instances	category	#instances
aeroplane	1285	bicycle	1208	boat	1397
bottle	2116	car	4008	cat	1616
chair	4338	diningtable	1057	dog	2079
horse	1156	person	15576	pottedplant	1724
sheep	1347	train	984	tvmonitor	1193

total	41084
[09/13 20:22:41 fsdet.data.detection_utils]: TransformGens used in training: [ResizeShortestEdge(short_edge_length=(480, 512, 544, 576, 608, 640, 672, 704, 736, 768, 800), max_size=1333, sample_style='choice'), RandomFlip()]
[09/13 20:22:41 fsdet.data.build]: Using training sampler TrainingSampler
[09/13 20:23:14 fvcore.common.checkpoint]: Loading checkpoint from checkpoints/pretrained_model/R-101.pkl
[09/13 20:23:14 fsdet.checkpoint.c2_model_loading]: Remapping C2 weights ......
[09/13 20:23:15 fsdet.checkpoint.c2_model_loading]: Some model parameters are not in the checkpoint:
backbone.fpn_lateral2.{bias, weight}
backbone.fpn_lateral3.{bias, weight}
backbone.fpn_lateral4.{bias, weight}
backbone.fpn_lateral5.{bias, weight}
backbone.fpn_output2.{bias, weight}
backbone.fpn_output3.{bias, weight}
backbone.fpn_output4.{bias, weight}
backbone.fpn_output5.{bias, weight}
proposal_generator.anchor_generator.cell_anchors.{0, 1, 2, 3, 4}
proposal_generator.rpn_head.anchor_deltas.{bias, weight}
proposal_generator.rpn_head.conv.{bias, weight}
proposal_generator.rpn_head.objectness_logits.{bias, weight}
roi_heads.box_head.fc1.{bias, weight}
roi_heads.box_head.fc2.{bias, weight}
roi_heads.box_predictor.bbox_pred.{bias, weight}
roi_heads.box_predictor.cls_score.{bias, weight}
[09/13 20:23:15 fsdet.checkpoint.c2_model_loading]: The checkpoint contains parameters not used by the model:
fc1000_b
fc1000_w
[09/13 20:23:15 fsdet.engine.train_loop]: Starting training from iteration 0
/home/wangyufei/anaconda3/envs/FSCE/lib/python3.6/multiprocessing/semaphore_tracker.py:143: UserWarning: semaphore_tracker: There appear to be 20 leaked semaphores to clean up at shutdown
len(cache))
Traceback (most recent call last):
File "tools/train_net.py", line 130, in

args=(args,),

File "/home/wangyufei/Code/FSCE/fsdet/engine/launch.py", line 49, in launch
daemon=False,
File "/home/wangyufei/anaconda3/envs/FSCE/lib/python3.6/site-packages/torch/multiprocessing/spawn.py", line 171, in spawn
while not spawn_context.join():
File "/home/wangyufei/anaconda3/envs/FSCE/lib/python3.6/site-packages/torch/multiprocessing/spawn.py", line 107, in join
(error_index, name)
Exception: process 0 terminated with signal SIGSEGV
(FSCE) [wangyufei@node03 FSCE]$ /home/wangyufei/anaconda3/envs/FSCE/lib/python3.6/multiprocessing/semaphore_tracker.py:143: UserWarning: semaphore_tracker: There appear to be 20 leaked semaphores to clean up at shutdown
len(cache))

(FSCE) [wangyufei@node03 FSCE]$

Problem with train config

I notice that config files for 1 shot and 2 shot set backbone.freeze, proposal_generator.freeze and roi_head.freeze_feat to True. Are these config flies (1shot and 2shot) the ones you used for FSCE performance? Or these are configs you used to reproduce TFA?

Training error

Dear authors,

When I run your code, there is an error. Could you give me some advice?

Code for visualization

Could you please provide the visualization code of the paper? Thank you very much!

Schedule of shot3, shot5, shot10 of pascal voc.

Sir, I cannot find the baseline config for pascal voc shot3, shot5, shot10, I guess the only change is the training schedule, could you tell me the schedule of them. Thanks in advance!

Unable to reproduce the FSCE result of pascal voc split1 shot3

Dear author, I am trying to reproduce your paper, but when I run the config of pascal voc split1 shot3, https://github.com/MegviiDetection/FSCE/blob/main/configs/PASCAL_VOC/split1/3shot_CL_IoU.yml, I get the result as follows:

[03/24 23:23:04 fsdet.evaluation.pascal_voc_evaluation]: Evaluating voc_2007_test_all1 using 2007 metric. Note that results do not use the official Matlab API.
[03/24 23:23:26 fsdet.evaluation.pascal_voc_evaluation]: Evaluate per-class mAP50:
|  aeroplane  |  bicycle  |  boat  |  bottle  |  car   |  cat   |  chair  |  diningtable  |  dog   |  horse  |  person  |  pottedplant  |  sheep  |  train  |  tvmonitor  |  bird  |  bus   |  cow   |  motorbike  |  sofa  |
|:-----------:|:---------:|:------:|:--------:|:------:|:------:|:-------:|:-------------:|:------:|:-------:|:--------:|:-------------:|:-------:|:-------:|:-----------:|:------:|:------:|:------:|:-----------:|:------:|
|   85.558    |  79.340   | 60.997 |  68.985  | 87.107 | 86.311 | 61.992  |    72.129     | 81.463 | 82.839  |  81.700  |    49.353     | 69.390  | 81.538  |   76.892    | 32.771 | 57.398 | 48.721 |   55.794    | 53.660 |
[03/24 23:23:26 fsdet.evaluation.pascal_voc_evaluation]: Evaluate overall bbox:
|   AP   |  AP50  |  AP75  |  bAP   |  bAP50  |  bAP75  |  nAP   |  nAP50  |  nAP75  |
|:------:|:------:|:------:|:------:|:-------:|:-------:|:------:|:-------:|:-------:|
| 39.492 | 68.697 | 40.156 | 43.895 | 75.040  | 45.338  | 26.281 | 49.669  | 24.610  |
[03/24 23:23:26 fsdet.engine.defaults]: Evaluation results for voc_2007_test_all1 in csv format:
[03/24 23:23:26 fsdet.evaluation.testing]: copypaste: Task: bbox
[03/24 23:23:26 fsdet.evaluation.testing]: copypaste: AP,AP50,AP75,bAP,bAP50,bAP75,nAP,nAP50,nAP75
[03/24 23:23:26 fsdet.evaluation.testing]: copypaste: 39.4919,68.6968,40.1564,43.8955,75.0396,45.3383,26.2812,49.6686,24.6105
[03/24 23:23:26 fsdet.utils.events]:  eta: 0:00:00  iter: 7999  total_loss: 0.3889  loss_cls: 0.09116  loss_box_reg: 0.08679  loss_contrast: 0.1952  loss_rpn_cls: 0.002133  loss_rpn_loc: 0.003993  time: 0.4631  data_time: 0.0475  lr: 0.00025  max_mem: 2057M
[03/24 23:23:26 fsdet.engine.hooks]: Overall training speed: 7996 iterations in 1:01:44 (0.4632 s / it)
[03/24 23:23:26 fsdet.engine.hooks]: Total training time: 1:46:03 (0:44:19 on hooks)

However, in paper the result is reported as 51.4, which is higher than my result 1.7% mAP:

Could you check the config if the setting are totally the same with that in the paper? Or if I did something wrong, this is my training command:

python tools/train_net.py --config-file configs/PASCAL_VOC/split1/3shot_CL_IoU.yml --num-gpus 8 MODEL.WEIGHTS models/model_reset_surgery.pth

Thanks in advance!

runtinmeError:Not compiled with GPU support

When I run the code ,I met the following problem" RuntinmeError:Not compiled with GPU support " dose anyone meet the same problem? my environment is pytorch1.71 cuda 10.1 GRX 2080Ti

problem when run build setup.py

when I try to build and run
python setup.py build develop

but I have already installed wheel

do I need to build detectron2?

No such file or directory: './configs/PascalVOC-detection/split1/faster_rcnn_R_101_FPN_ft_all1_1shot.yaml'

Could you please provide these files for following command?Thank you!

python tools/run_experiments.py --num-gpus 2 --shots 1 2 3 5 10 --seeds 0 30 --split 1

train_net.py: error: unrecognized arguments: --opts

I am confused why --opts can not use?

python tools/train_net.py --num-gpus 8         \
--config-file configs/PASCAL_VOC/split1/10shot_CL_IoU.yml \
--opts MODEL.WEIGHTS  checkpoints/voc/faster_rcnn/faster_rcnn_R_101_FPN_all1/model_reset_surgery.pth

Problems encountered in visualization

After running the model, I want to use the “demo/demo.py” to randomly input a picture for detection.

python demo/demo.py --config-file configs/PASCAL_VOC/base-training/R101_FPN_base_training_split1.yml \--input input1.jpg
Here I can normally detect the results and output a picture with the detection results.But，in the fine tune model，after I do this
python demo/demo.py --config-file configs/PASCAL_VOC/split1/10shot_CL_IoU.yml \--input input1.jpg
The content of the error report is
AssertionError: get_event_storage() has to be called inside a 'with EventStorage(...)' context!
I appreciate anyone who can help me.

Confusion about the experiment config of COCO

Hi, I find that the config files of experiments on COCO datasets you provide is based on the strong baseline mentioned in the paper? So the contrastive loss does not work on COCO or for some other reasons?Look forward to your reply,thank you.

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.