mdv3101 / cdecnet Goto Github PK

I tried to use the docker container with the image_demo.py.
Running the default docker container in the repo gives me the error, that mmcv is missing.
So I added:

RUN pip install mmcv-full==latest+torch1.5.0+cu101 -f https://openmmlab.oss-accelerate.aliyuncs.com/mmcv/dist/index.html

from https://github.com/open-mmlab/mmdetection/blob/master/docker/Dockerfile.
when running the demo i get:

  File "demo/image_demo.py", line 26, in <module>
    main()
  File "demo/image_demo.py", line 18, in main
    model = init_detector(args.config, args.checkpoint, device=args.device)
  File "/mmdetection/mmdet/apis/inference.py", line 39, in init_detector
    model = build_detector(config.model, test_cfg=config.get('test_cfg'))
  File "/mmdetection/mmdet/models/builder.py", line 77, in build_detector
    return build(cfg, DETECTORS, dict(train_cfg=train_cfg, test_cfg=test_cfg))
  File "/mmdetection/mmdet/models/builder.py", line 34, in build
    return build_from_cfg(cfg, registry, default_args)
  File "/opt/conda/lib/python3.7/site-packages/mmcv/utils/registry.py", line 182, in build_from_cfg
    raise type(e)(f'{obj_cls.__name__}: {e}')
KeyError: "CascadeRCNN: 'DB_ResNeXt is not in the backbone registry' "

I saw #11 but I thought the docker container installs everything properly for me.
Any suggestions on how I should change the dockerfile to get the dependencies installed properly?

Hi, I'd like to re-train your model with IIIT-AR-13K dataset. Do you mind sharing the link to download it? Thank you in advance.

Hi @mdv3101, thanks for the awesome project.
I am trying to run inference with the pre-trained model but i am getting the following error:
My environment is colab notebook and I followed steps from install.md

Traceback (most recent call last):
  File "/content/CDeCNet/demo/image_demo.py", line 28, in <module>
    main()
  File "/content/CDeCNet/demo/image_demo.py", line 20, in main
    model = init_detector(args.config, args.checkpoint, device=args.device)
  File "/content/CDeCNet/mmdet/apis/inference.py", line 36, in init_detector
    if 'CLASSES' in checkpoint['meta']:
KeyError: 'meta' 

my command is:

!python demo/image_demo.py <image> configs/dcn/db_cascade_mask_rcnn_x101_fpn_dconv_c3-c5_1x_coco.py \
    /gdrive/MyDrive/table_detection_model/db_cascade_mask_rcnn_x101_32x4d_fpn_dconv_c3-c5_1x_coco-e75f90c8.pth \
    --score-thr 0.95 --output-img 'output_demo.jpg'

in the installation step i tried both pip and setup install, but both are giving me same error. is there a mismatch between my pretrain and config file. Thanks in advance.

Hi,

I was wondering if you could provide support to run the inferencing alone on CPU? Currently Deformable CNNs are supported only in CUDA OPS and do not have a vanilla torch implementation. Do you plan to implement this in the future?

Thank you,
Nandhinee

I want to train CDeCNet for my dataset. I tried to setup the project in my ubuntu machine. I followed the steps as mentioned.

In the step: pip install "git+https://github.com/open-mmlab/cocoapi.git#subdirectory=pycocotools"

I am getting following error:

Building wheel for mmpycocotools (setup.py) ... error
  ERROR: Command errored out with exit status 1:
   command: /xxx/Python/miniconda3/envs/torch1.5cu101/bin/python -u -c 'import sys, setuptools, tokenize; sys.argv[0] = '"'"'/tmp/pip-req-build-zlq4o34_/pycocotools/setup.py'"'"'; __file__='"'"'/tmp/pip-req-build-zlq4o34_/pycocotools/setup.py'"'"';f=getattr(tokenize, '"'"'open'"'"', open)(__file__);code=f.read().replace('"'"'\r\n'"'"', '"'"'\n'"'"');f.close();exec(compile(code, __file__, '"'"'exec'"'"'))' bdist_wheel -d /tmp/pip-wheel-izl_v7fr
       cwd: /tmp/pip-req-build-zlq4o34_/pycocotools
  Complete output (63 lines):
  running bdist_wheel
  running build
  running build_py
  creating build
  creating build/lib.linux-x86_64-3.7
  creating build/lib.linux-x86_64-3.7/pycocotools
  copying pycocotools/__init__.py -> build/lib.linux-x86_64-3.7/pycocotools
  copying pycocotools/cocoeval.py -> build/lib.linux-x86_64-3.7/pycocotools
  copying pycocotools/coco.py -> build/lib.linux-x86_64-3.7/pycocotools
  copying pycocotools/mask.py -> build/lib.linux-x86_64-3.7/pycocotools
  running build_ext
  building 'pycocotools._mask' extension
  creating build/temp.linux-x86_64-3.7
  creating build/temp.linux-x86_64-3.7/common
  creating build/temp.linux-x86_64-3.7/pycocotools
  gcc -pthread -B /xxx/Python/miniconda3/envs/torch1.5cu101/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/xxx/Python/miniconda3/envs/torch1.5cu101/lib/python3.7/site-packages/numpy/core/include -Icommon -I/xxx/Softies/Python/miniconda3/envs/torch1.5cu101/include/python3.7m -c common/maskApi.c -o build/temp.linux-x86_64-3.7/common/maskApi.o
  common/maskApi.c: In function ‘rleDecode’:
  common/maskApi.c:46:7: warning: this ‘for’ clause does not guard... [-Wmisleading-indentation]
         for( k=0; k<R[i].cnts[j]; k++ ) *(M++)=v; v=!v; }}
         ^~~
  common/maskApi.c:46:49: note: ...this statement, but the latter is misleadingly indented as if it were guarded by the ‘for’
         for( k=0; k<R[i].cnts[j]; k++ ) *(M++)=v; v=!v; }}
                                                   ^
  common/maskApi.c: In function ‘rleFrPoly’:
  common/maskApi.c:166:3: warning: this ‘for’ clause does not guard... [-Wmisleading-indentation]
     for(j=0; j<k; j++) x[j]=(int)(scale*xy[j*2+0]+.5); x[k]=x[0];
     ^~~
  common/maskApi.c:166:54: note: ...this statement, but the latter is misleadingly indented as if it were guarded by the ‘for’
     for(j=0; j<k; j++) x[j]=(int)(scale*xy[j*2+0]+.5); x[k]=x[0];
                                                        ^
  common/maskApi.c:167:3: warning: this ‘for’ clause does not guard... [-Wmisleading-indentation]
     for(j=0; j<k; j++) y[j]=(int)(scale*xy[j*2+1]+.5); y[k]=y[0];
     ^~~
  common/maskApi.c:167:54: note: ...this statement, but the latter is misleadingly indented as if it were guarded by the ‘for’
     for(j=0; j<k; j++) y[j]=(int)(scale*xy[j*2+1]+.5); y[k]=y[0];
                                                        ^
  common/maskApi.c: In function ‘rleToString’:
  common/maskApi.c:212:7: warning: this ‘if’ clause does not guard... [-Wmisleading-indentation]
         if(more) c |= 0x20; c+=48; s[p++]=c;
         ^~
  common/maskApi.c:212:27: note: ...this statement, but the latter is misleadingly indented as if it were guarded by the ‘if’
         if(more) c |= 0x20; c+=48; s[p++]=c;
                             ^
  common/maskApi.c: In function ‘rleFrString’:
  common/maskApi.c:220:3: warning: this ‘while’ clause does not guard... [-Wmisleading-indentation]
     while( s[m] ) m++; cnts=malloc(sizeof(uint)*m); m=0;
     ^~~~~
  common/maskApi.c:220:22: note: ...this statement, but the latter is misleadingly indented as if it were guarded by the ‘while’
     while( s[m] ) m++; cnts=malloc(sizeof(uint)*m); m=0;
                        ^~~~
  common/maskApi.c:228:5: warning: this ‘if’ clause does not guard... [-Wmisleading-indentation]
       if(m>2) x+=(long) cnts[m-2]; cnts[m++]=(uint) x;
       ^~
  common/maskApi.c:228:34: note: ...this statement, but the latter is misleadingly indented as if it were guarded by the ‘if’
       if(m>2) x+=(long) cnts[m-2]; cnts[m++]=(uint) x;
                                    ^~~~
  common/maskApi.c: In function ‘rleToBbox’:
  common/maskApi.c:141:31: warning: ‘xp’ may be used uninitialized in this function [-Wmaybe-uninitialized]
         if(j%2==0) xp=x; else if(xp<x) { ys=0; ye=h-1; }
                                 ^
  gcc -pthread -B /xxx/Softies/Python/miniconda3/envs/torch1.5cu101/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/xxx/Softies/Python/miniconda3/envs/torch1.5cu101/lib/python3.7/site-packages/numpy/core/include -Icommon -I/xxx/Softies/Python/miniconda3/envs/torch1.5cu101/include/python3.7m -c pycocotools/_mask.c -o build/temp.linux-x86_64-3.7/pycocotools/_mask.o
  gcc: error: pycocotools/_mask.c: No such file or directory
  error: command 'gcc' failed with exit status 1
  ----------------------------------------
  ERROR: Failed building wheel for mmpycocotools

Environment:

addict==2.4.0
certifi==2020.11.8
cycler==0.10.0
Cython==0.29.21
kiwisolver==1.3.1
matplotlib==3.3.3
mkl-fft==1.2.0
mkl-random==1.1.1
mkl-service==2.3.0
mmcv==1.1.5
mmdet==2.7.0
mmpycocotools==12.0.3
numpy @ file:///tmp/build/80754af9/numpy_and_numpy_base_1603479632437/work
olefile==0.46
opencv-python==4.4.0.46
Pillow==6.2.2
pyparsing==2.4.7
python-dateutil==2.8.1
PyYAML==5.3.1
six @ file:///tmp/build/80754af9/six_1605205313296/work
terminaltables==3.1.0
torch==1.4.0
torchvision==0.5.0
yapf==0.30.0

And after this if still I run pip install -v -e .
I am facing errors like:

In file included from /XXX/CDeCNet/mmdet/ops/nms/src/cuda/nms_kernel.cu:3:0:
    /xxx/Python/miniconda3/envs/torch1.5cu101/lib/python3.7/site-packages/torch/include/ATen/cuda/CUDAContext.h:7:10: fatal error: cublas_v2.h: No such file or directory
     #include <cublas_v2.h>
              ^~~~~~~~~~~~~
    compilation terminated.

Hello, I am using your open source code to identify the picture table。I'm using this config file(dcn/db_cascade_mask_rcnn_x101_fpn_dconv_c3-c5_1x_coco.py) and checkpoint file(tablebank_sota.pth)。But the runtime error is:TypeError: init() got an unexpected keyword argument 'roi_head'，I wonder if this is caused by a mismatch between the config file and the checkpoint file.

Please help. Following the same guidelines as suggested

File "/home/devteam/.local/lib/python3.8/site-packages/torch/serialization.py", line 116, in validate_cuda_device
raise RuntimeError('Attempting to deserialize object on a CUDA '
RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.

What is the difference between in single model CDeC-Net‡and CDeC-Net?
Can you provide the pretrained models for single model CDeC-Net‡ in PubLayNet?
Thanks!

Can we use checkpoints for training the model for cell and table detection at the same time?

Hello,
I am trying to use the base model trained on IIIT-AR-13K dataset. When executing the demo script, I face the error: RuntimeError: deform conv is not compiled with GPU support (deform_conv_forward at mmdet/ops/dcn/src/deform_conv_ext.cpp:63) which caused because the variable WITH_CUDA in the file deform_conv_ext.cpp is not defined. I can not manage to know where/how this variable is supposed to be defined.
I installed all the packages with the required dependency except for cuda: torch.version.cuda is 10.1 and not 10.0.
Could the faced error be caused by this versions mismatches?
Thanks

hello~
When I ran the program, I found this error. Do you know how to solve it,

Traceback (most recent call last):
File "tools/train.py", line 161, in
main()
File "tools/train.py", line 157, in main
meta=meta)
File "/home/jsj201-2/mount1/lxy/CDeCNet/mmdet/apis/train.py", line 179, in train_detector
runner.run(data_loaders, cfg.workflow, cfg.total_epochs)
File "/home/jsj201-2/.conda/envs/open-mmlab/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 125, inrun
epoch_runner(data_loaders[i], **kwargs)
File "/home/jsj201-2/.conda/envs/open-mmlab/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 47, in train
for i, data_batch in enumerate(self.data_loader):
File "/home/jsj201-2/.conda/envs/open-mmlab/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 345, in next
data = self._next_data()
File "/home/jsj201-2/.conda/envs/open-mmlab/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 856, in _next_data
return self._process_data(data)
File "/home/jsj201-2/.conda/envs/open-mmlab/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 881, in _process_data
data.reraise()
File "/home/jsj201-2/.conda/envs/open-mmlab/lib/python3.7/site-packages/torch/_utils.py", line 394, in reraise
raise self.exc_type(msg)
TypeError: Caught TypeError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/home/jsj201-2/.conda/envs/open-mmlab/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 178, in_worker_loop
data = fetcher.fetch(index)
File "/home/jsj201-2/.conda/envs/open-mmlab/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/jsj201-2/.conda/envs/open-mmlab/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/jsj201-2/mount1/lxy/CDeCNet/mmdet/datasets/custom.py", line 144, in getitem
data = self.prepare_train_img(idx)
File "/home/jsj201-2/mount1/lxy/CDeCNet/mmdet/datasets/custom.py", line 157, in prepare_train_img
return self.pipeline(results)
File "/home/jsj201-2/mount1/lxy/CDeCNet/mmdet/datasets/pipelines/compose.py", line 25, in call
data = t(data)
File "/home/jsj201-2/mount1/lxy/CDeCNet/mmdet/datasets/pipelines/transforms.py", line 306, in call
self._pad_masks(results)
File "/home/jsj201-2/mount1/lxy/CDeCNet/mmdet/datasets/pipelines/transforms.py", line 298, in _pad_masks
pad_shape[:2], pad_val=self.pad_val)
File "/home/jsj201-2/mount1/lxy/CDeCNet/mmdet/core/mask/structures.py", line 179, in pad
for mask in self.masks
File "/home/jsj201-2/mount1/lxy/CDeCNet/mmdet/core/mask/structures.py", line 179, in
for mask in self.masks
TypeError: impad() takes 1 positional argument but 2 positional arguments (and 1 keyword-only argument) were given

I hope you can help me solve this problem. Thank you very much

I try to test an image use the config flie from https://github.com/mdv3101/CDeCNet/blob/master/configs/dcn/db_cascade_mask_rcnn_x101_fpn_dconv_c3-c5_1x_coco.py ,
and checkpoint file from your result table called "tablebank_sota.pth" (https://drive.google.com/file/d/1CGVE5IBaGL6Ssh7dKMv8csz3omezd_HX/view) , but get the error like this. can you give some advice ?

I am getting these issues while instaling: I have issues with coverage. if I put it as 4.4 there's error to make it 3.7.1 if I do that It suggest me to go back

ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behavior is the source of the following dependency conflicts. datascience 0.10.6 requires coverage==3.7.1, but you have coverage 4.4 which is incompatible. datascience 0.10.6 requires folium==0.2.1, but you have folium 0.10.1 which is incompatible. coveralls 0.5 requires coverage<3.999,>=3.6, but you have coverage 4.4 which is incompatible.

if I manually change it,

ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts. pytest-cov 2.9.0 requires coverage>=4.4, but you have coverage 3.7.1 which is incompatible. datascience 0.10.6 requires folium==0.2.1, but you have folium 0.10.1 which is incompatible.

can someone help me resolve these dependency issues?

Appreciate greatly the great work done by you guys.
I am trying to run image_demo.py on the PubLayNet downloaded from the link provided. The result does not have any bounding box for table. I am getting the following messages in the console:

/usr/local/lib/python3.7/dist-packages/mmcv/utils/misc.py:304: UserWarning: "out_size" is deprecated in RoIAlign.__init__, please use "output_size" instead
f'"{src_arg_name}" is deprecated in '
/usr/local/lib/python3.7/dist-packages/mmcv/utils/misc.py:304: UserWarning: "sample_num" is deprecated in RoIAlign.__init__, please use "sampling_ratio" instead
f'"{src_arg_name}" is deprecated in '
_The model and loaded state dict do not match exactly

size mismatch for backbone.layer1.0.conv1.weight: copying a param with shape torch.Size([128, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]).
size mismatch for backbone.layer1.0.bn1.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([64])._

Appreciate your help with this issue.

I am interesting in using CDeCNet for detecting tables in annual reports. Thus, I tried to use your base model. I downloded the checkpoint that you shared (the file name is epoch_50.pth). After that I tried to use it with image from the dataset IIIT-AR-13K. I used mmdet.apis as suggested in the scrip https://github.com/mdv3101/CDeCNet/blob/master/demo/image_demo.py. I used the config file https://github.com/mdv3101/CDeCNet/blob/master/configs/cascade_rcnn/db_cascade_mask_rcnn_x101_32x4d_fpn_1x_coco.py. The script runs fine but no tables are detected ie the result returned by the command inference_detector(model, img) is empty. I am wondering if I am using the wrong checkpoint file or the wrong config.
Thanks.

$ python demo/image_demo.py border_less2.jpg configs/dcn/db_cascade_mask_rcnn_x101_fpn_dconv_c3-c5_1x_coco.py /home/devteam/CDeCNet/model/epoch_50.pth --device 'cpu' --score-thr 0.95 --output-img 'output_demo.jpg'
which: no nvcc in (/home/devteam/.conda/envs/py38/bin:/opt/miniconda3/condabin:/home/devteam/.local/bin:/home/devteam/bin:/usr/local/bin:/usr/bin:/usr/local/sbin:/usr/sbin:/opt/miniconda3/bin)

/home/devteam/CDeCNet/mmdet/apis/inference.py(37)init_detector()

-> if checkpoint is not None:
(Pdb) c

/home/devteam/CDeCNet/mmdet/apis/inference.py(91)inference_detector()
-> if next(model.parameters()).is_cuda:
(Pdb) c
/home/devteam/CDeCNet/mmdet/apis/inference.py:91: UserWarning: We set use_torchvision=True in CPU mode.
if next(model.parameters()).is_cuda:
Traceback (most recent call last):
File "demo/image_demo.py", line 28, in
main()
File "demo/image_demo.py", line 22, in main
result = inference_detector(model, args.img)
File "/home/devteam/CDeCNet/mmdet/apis/inference.py", line 91, in inference_detector
if next(model.parameters()).is_cuda:
File "/home/devteam/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/home/devteam/CDeCNet/mmdet/core/fp16/decorators.py", line 51, in new_func
return old_func(*args, **kwargs)
File "/home/devteam/CDeCNet/mmdet/models/detectors/base.py", line 148, in forward
return self.forward_test(img, img_metas, **kwargs)
File "/home/devteam/CDeCNet/mmdet/models/detectors/base.py", line 129, in forward_test
return self.simple_test(imgs[0], img_metas[0], **kwargs)
File "/home/devteam/CDeCNet/mmdet/models/detectors/two_stage.py", line 184, in simple_test
x = self.extract_feat(img)
File "/home/devteam/CDeCNet/mmdet/models/detectors/two_stage.py", line 76, in extract_feat
x = self.backbone(img)
File "/home/devteam/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/home/devteam/CDeCNet/mmdet/models/backbones/db_resnet.py", line 714, in forward
second_x = second_res_layer(second_x)
File "/home/devteam/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/home/devteam/.local/lib/python3.8/site-packages/torch/nn/modules/container.py", line 100, in forward
input = module(input)
File "/home/devteam/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/home/devteam/CDeCNet/mmdet/models/backbones/db_resnet.py", line 280, in forward
out = _inner_forward(x)
File "/home/devteam/CDeCNet/mmdet/models/backbones/db_resnet.py", line 257, in _inner_forward
out = self.conv2(out)
File "/home/devteam/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/home/devteam/CDeCNet/mmdet/ops/dcn/deform_conv.py", line 295, in forward
return deform_conv(x, offset, self.weight, self.stride, self.padding,
File "/home/devteam/CDeCNet/mmdet/ops/dcn/deform_conv.py", line 47, in forward
raise NotImplementedError
NotImplementedError

I didn't see any demo folder in the repo for a single image testing.

Having a hard time setting up mm-detection without GPU any suggestions?

After changing all the codes as per my system/cuda I tried running.
But I am facing the below error, could you please help me.

2023-02-07 16:12:29,370 - root - INFO - load model from: open-mmlab://resnext101_32x4d
Traceback (most recent call last):
File "tools/train.py", line 161, in
main()
File "tools/train.py", line 134, in main
cfg.model, train_cfg=cfg.train_cfg, test_cfg=cfg.test_cfg)
File "/home/gautam8/CDeCNet/mmdet/models/builder.py", line 48, in build_detector
return build(cfg, DETECTORS, dict(train_cfg=train_cfg, test_cfg=test_cfg))
File "/home/gautam8/CDeCNet/mmdet/models/builder.py", line 20, in build
return build_from_cfg(cfg, registry, default_args)
File "/home/gautam8/.local/lib/python3.6/site-packages/mmcv/utils/registry.py", line 168, in build_from_cfg
return obj_cls(**args)
File "/home/gautam8/CDeCNet/mmdet/models/detectors/cascade_rcnn.py", line 23, in init
pretrained=pretrained)
File "/home/gautam8/CDeCNet/mmdet/models/detectors/two_stage.py", line 49, in init
self.init_weights(pretrained=pretrained)
File "/home/gautam8/CDeCNet/mmdet/models/detectors/two_stage.py", line 61, in init_weights
self.backbone.init_weights(pretrained=pretrained)
File "/home/gautam8/CDeCNet/mmdet/models/backbones/db_resnet.py", line 637, in init_weights
load_checkpoint(self, pretrained, strict=False, logger=logger)
File "/home/gautam8/.local/lib/python3.6/site-packages/mmcv/runner/checkpoint.py", line 211, in load_checkpoint
checkpoint = _load_checkpoint(filename, map_location)
File "/home/gautam8/.local/lib/python3.6/site-packages/mmcv/runner/checkpoint.py", line 183, in _load_checkpoint
checkpoint = load_url_dist(open_mmlab_model_urls[model_name])
File "/home/gautam8/.local/lib/python3.6/site-packages/mmcv/runner/checkpoint.py", line 139, in load_url_dist
checkpoint = model_zoo.load_url(url)
File "/home/gautam8/.local/lib/python3.6/site-packages/torch/hub.py", line 506, in load_state_dict_from_url
return torch.load(cached_file, map_location=map_location)
File "/home/gautam8/.local/lib/python3.6/site-packages/torch/serialization.py", line 529, in load
return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
File "/home/gautam8/.local/lib/python3.6/site-packages/torch/serialization.py", line 709, in _legacy_load
deserialized_objects[key]._set_from_file(f, offset, f_should_read_directly)
RuntimeError: unexpected EOF, expected 59 more bytes. The file might be corrupted.

I am getting error "ImportError: DLL load failed: The specified procedure could not be found."-- referring to deform_conv_ext.cp37-win_amd64.pyd file from deform_layer. I am trying to run the repo on windows 10. I have followed the steps mentioned in readme. Could you please suggest how to run this on windows 10.

when I want to test model in image_demo.py that copy from 'mmdetection' ,report error

RuntimeError: CUDA error: no kernel image is available for execution on the device (launch_kernel at /pytorch/aten/src/ATen/native/cuda/Loops.cuh:103)
frame # 0: c10::Error::Error(c10::SourceLocation, std::string const&) + 0x33 (0x7fac76d7b193 in /home/wang388/346/envs/open-mmlab/lib/python3.7/site-packages/torch/lib/libc10.so)
frame # 1: void at::native::gpu_index_kernel<__nv_dl_wrapper_t<__nv_dl_tag<void ()(at::TensorIterator&, c10::ArrayRef, c10::ArrayRef), &(void at::native::index_kernel_impl<at::native::OpaqueType<8> >(at::TensorIterator&, c10::ArrayRef, c10::ArrayRef)), 1u>> >(at::TensorIterator&, c10::ArrayRef, c10::ArrayRef, __nv_dl_wrapper_t<__nv_dl_tag<void ()(at::TensorIterator&, c10::ArrayRef, c10::ArrayRef), &(void at::native::index_kernel_impl<at::native::OpaqueType<8> >(at::TensorIterator&, c10::ArrayRef, c10::ArrayRef)), 1u>> const&) + 0x7bb (0x7fabf16bc87b in /home/wang388/346/envs/open-mmlab/lib/python3.7/site-packages/torch/lib/libtorch.so)
frame # 2: + 0x580fc32 (0x7fabf16b6c32 in /home/wang388/346/envs/open-mmlab/lib/python3.7/site-packages/torch/lib/libtorch.so)
frame # 3: + 0x580ff88 (0x7fabf16b6f88 in /home/wang388/346/envs/open-mmlab/lib/python3.7/site-packages/torch/lib/libtorch.so)
frame # 4: + 0x1a7493b (0x7fabed91b93b in /home/wang388/346/envs/open-mmlab/lib/python3.7/site-packages/torch/lib/libtorch.so)
frame # 5: at::native::index(at::Tensor const&, c10::ArrayRefat::Tensor) + 0x47e (0x7fabed9176fe in /home/wang388/346/envs/open-mmlab/lib/python3.7/site-packages/torch/lib/libtorch.so)
frame # 6: + 0x1fe06aa (0x7fabede876aa in /home/wang388/346/envs/open-mmlab/lib/python3.7/site-packages/torch/lib/libtorch.so)
frame # 7: + 0x1fe5173 (0x7fabede8c173 in /home/wang388/346/envs/open-mmlab/lib/python3.7/site-packages/torch/lib/libtorch.so)
frame # 8: + 0x3bffe6a (0x7fabefaa6e6a in /home/wang388/346/envs/open-mmlab/lib/python3.7/site-packages/torch/lib/libtorch.so)
frame # 9: + 0x1fe5173 (0x7fabede8c173 in /home/wang388/346/envs/open-mmlab/lib/python3.7/site-packages/torch/lib/libtorch.so)
frame # 10: at::Tensor::index(c10::ArrayRefat::Tensor) const + 0x191 (0x7fac7b99d921 in /home/wang388/346/envs/open-mmlab/lib/python3.7/site-packages/torch/lib/libtorch_python.so)
frame # 11: nms_cuda_forward(at::Tensor, float) + 0x85f (0x7fac587fef1a in /home/wang388/346/envs/open-mmlab/lib/python3.7/site-packages/mmdet-2.0.0+e05e858-py3.7-linux-x86_64.egg/mmdet/ops/nms/nms_ext.cpython-37m-x86_64-linux-gnu.so)

the version of CUDA is 10.0.130
the version of pytorch is 1.4.0
the version of Torchvision is 0.5

thanks

Hello, I would like to ask if it can detect wireless forms

Can you please explain this part of the readme file else can add the data folder or link from where we can download it.

Can you re-provide the weights of this model, the link is broken