Comments (4)
Thanks for your interest! Please refer to the following onedrive link.
from sigma.
Thank you very much, this seems to only log into your school email, I downloaded this dataset via another URL: https://download.openmmlab.com/pretrain/third_party/vgg16_caffe-292e1171.pth.
Built the environment, but there is a problem at fcos_core/modeling/rpn/fcos/inference.py under line 77:
Traceback (most recent call last):
File "tools/train_net_da.py", line 20, in
from fcos_core.modeling.detector import build_detection_model
File "/media/ubuntu/9a32be42-b1fc-4942-91da-4a28a2388ede/zyb/SCAN/fcos_core/modeling/detector/init.py", line 2, in
from .detectors import build_detection_model
File "/media/ubuntu/9a32be42-b1fc-4942-91da-4a28a2388ede/zyb/SCAN/fcos_core/modeling/detector/detectors.py", line 2, in
from .generalized_rcnn import GeneralizedRCNN
File "/media/ubuntu/9a32be42-b1fc-4942-91da-4a28a2388ede/zyb/SCAN/fcos_core/modeling/detector/generalized_rcnn.py", line 11, in
from ..backbone import build_backbone
File "/media/ubuntu/9a32be42-b1fc-4942-91da-4a28a2388ede/zyb/SCAN/fcos_core/modeling/backbone/init.py", line 3, in
from . import fbnet
File "/media/ubuntu/9a32be42-b1fc-4942-91da-4a28a2388ede/zyb/SCAN/fcos_core/modeling/backbone/fbnet.py", line 14, in
from fcos_core.modeling.rpn import rpn
File "/media/ubuntu/9a32be42-b1fc-4942-91da-4a28a2388ede/zyb/SCAN/fcos_core/modeling/rpn/rpn.py", line 9, in
from fcos_core.modeling.rpn.fcos.fcos import build_fcos
File "/media/ubuntu/9a32be42-b1fc-4942-91da-4a28a2388ede/zyb/SCAN/fcos_core/modeling/rpn/fcos/fcos.py", line 5, in
from .inference import make_fcos_postprocessor
File "/media/ubuntu/9a32be42-b1fc-4942-91da-4a28a2388ede/zyb/SCAN/fcos_core/modeling/rpn/fcos/inference.py", line 77
pre_nms_top_n = pre_nms_top_n.clamp(max=self.pre_nms_top_n)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
^
SyntaxError: invalid syntax
Have you encountered this problem and what should I do to fix it?Thanks!
from sigma.
Thank you very much, this seems to only log into your school email, I downloaded this dataset via another URL: https://download.openmmlab.com/pretrain/third_party/vgg16_caffe-292e1171.pth. Built the environment, but there is a problem at fcos_core/modeling/rpn/fcos/inference.py under line 77: Traceback (most recent call last): File "tools/train_net_da.py", line 20, in from fcos_core.modeling.detector import build_detection_model File "/media/ubuntu/9a32be42-b1fc-4942-91da-4a28a2388ede/zyb/SCAN/fcos_core/modeling/detector/init.py", line 2, in from .detectors import build_detection_model File "/media/ubuntu/9a32be42-b1fc-4942-91da-4a28a2388ede/zyb/SCAN/fcos_core/modeling/detector/detectors.py", line 2, in from .generalized_rcnn import GeneralizedRCNN File "/media/ubuntu/9a32be42-b1fc-4942-91da-4a28a2388ede/zyb/SCAN/fcos_core/modeling/detector/generalized_rcnn.py", line 11, in from ..backbone import build_backbone File "/media/ubuntu/9a32be42-b1fc-4942-91da-4a28a2388ede/zyb/SCAN/fcos_core/modeling/backbone/init.py", line 3, in from . import fbnet File "/media/ubuntu/9a32be42-b1fc-4942-91da-4a28a2388ede/zyb/SCAN/fcos_core/modeling/backbone/fbnet.py", line 14, in from fcos_core.modeling.rpn import rpn File "/media/ubuntu/9a32be42-b1fc-4942-91da-4a28a2388ede/zyb/SCAN/fcos_core/modeling/rpn/rpn.py", line 9, in from fcos_core.modeling.rpn.fcos.fcos import build_fcos File "/media/ubuntu/9a32be42-b1fc-4942-91da-4a28a2388ede/zyb/SCAN/fcos_core/modeling/rpn/fcos/fcos.py", line 5, in from .inference import make_fcos_postprocessor File "/media/ubuntu/9a32be42-b1fc-4942-91da-4a28a2388ede/zyb/SCAN/fcos_core/modeling/rpn/fcos/inference.py", line 77 pre_nms_top_n = pre_nms_top_n.clamp(max=self.pre_nms_top_n)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 ^ SyntaxError: invalid syntax Have you encountered this problem and what should I do to fix it?Thanks!
Hi, sorry for the wrong link. I have corrected it as this.
It seems that the project was built successfully. Did you use the DAOD benchmark dataset or your custom one? Are you running SCAN or SIGMA? SIGMA is a much more robust version.
Finally, I haven't met such an issue before... I can try to help you if you can provide more details about your experiments.
from sigma.
Thanks for the reply! This is the cityscapes dataset run on SCAN. I will reproduce SIGMA and if I have any questions I will ask you again, thanks again for your excellent contribution.
I tried changing pre_nms_top_n = candidate_inds.view(N, -1).sum(1) to pre_nms_top_n = candidate_inds.reshape(N, -1).sum(1), and now it seems to work! Here is a preliminary run at cityscapes to cityscapes_foggy, is this correct?
2024-06-30 15:05:21,652 fcos_core.trainer INFO: Start training
/home/ubuntu/anaconda3/envs/SCAN/lib/python3.7/site-packages/torch/functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2157.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
2024-06-30 15:06:22,992 fcos_core.trainer INFO: eta: 2 days, 20:08:05 iter: 20 loss_gs: 5.0374 (5.9095) node_loss_gs: 2.1283 (2.1133) act_loss_gs: 0.1318 (0.3350) loss_cls_gs: 0.6337 (0.6870) loss_reg_gs: 1.4703 (2.1026) loss_centerness_gs: 0.6661 (0.6716) loss_ds: 0.3457 (0.3460) zeros: 0.0000 (0.0000) loss_adv_P7_CON_ds: 0.0702 (0.0703) loss_adv_P6_CON_ds: 0.0696 (0.0696) loss_adv_P5_CON_ds: 0.0685 (0.0685) loss_adv_P4_CON_ds: 0.0692 (0.0692) loss_adv_P3_CON_ds: 0.0682 (0.0684) loss_dt: 0.3476 (0.3476) zero_gt: 0.0000 (0.0000) loss_adv_P7_CON_dt: 0.0685 (0.0684) loss_adv_P6_CON_dt: 0.0691 (0.0692) loss_adv_P5_CON_dt: 0.0702 (0.0702) loss_adv_P4_CON_dt: 0.0695 (0.0695) loss_adv_P3_CON_dt: 0.0704 (0.0703) time: 2.9972 (3.0668) data: 0.0077 (0.1001) lr_backbone: 0.000833 lr_middle_head: 0.000833 lr_fcos: 0.000833 lr_dis: 0.000833 max mem: 6198
2024-06-30 15:07:22,839 fcos_core.trainer INFO: eta: 2 days, 19:17:24 iter: 40 loss_gs: 4.0197 (4.9547) node_loss_gs: 1.6470 (1.8859) act_loss_gs: 0.0988 (0.2172) loss_cls_gs: 0.4741 (0.5811) loss_reg_gs: 1.0964 (1.6047) loss_centerness_gs: 0.6601 (0.6658) loss_ds: 0.3457 (0.3458) zeros: 0.0000 (0.0000) loss_adv_P7_CON_ds: 0.0703 (0.0703) loss_adv_P6_CON_ds: 0.0694 (0.0695) loss_adv_P5_CON_ds: 0.0685 (0.0685) loss_adv_P4_CON_ds: 0.0693 (0.0692) loss_adv_P3_CON_ds: 0.0681 (0.0683) loss_dt: 0.3479 (0.3477) zero_gt: 0.0000 (0.0000) loss_adv_P7_CON_dt: 0.0685 (0.0685) loss_adv_P6_CON_dt: 0.0693 (0.0692) loss_adv_P5_CON_dt: 0.0702 (0.0702) loss_adv_P4_CON_dt: 0.0694 (0.0694) loss_adv_P3_CON_dt: 0.0706 (0.0704) time: 3.0055 (3.0296) data: 0.0086 (0.0602) lr_backbone: 0.000833 lr_middle_head: 0.000833 lr_fcos: 0.000833 lr_dis: 0.000833 max mem: 6491
2024-06-30 15:08:22,805 fcos_core.trainer INFO: eta: 2 days, 19:02:31 iter: 60 loss_gs: 4.1649 (4.6570) node_loss_gs: 1.3220 (1.7088) act_loss_gs: 0.0711 (0.1687) loss_cls_gs: 0.9412 (0.7075) loss_reg_gs: 1.0037 (1.4089) loss_centerness_gs: 0.6574 (0.6631) loss_ds: 0.3455 (0.3457) zeros: 0.0000 (0.0000) loss_adv_P7_CON_ds: 0.0702 (0.0703) loss_adv_P6_CON_ds: 0.0692 (0.0694) loss_adv_P5_CON_ds: 0.0687 (0.0686) loss_adv_P4_CON_ds: 0.0695 (0.0693) loss_adv_P3_CON_ds: 0.0679 (0.0681) loss_dt: 0.3480 (0.3478) zero_gt: 0.0000 (0.0000) loss_adv_P7_CON_dt: 0.0685 (0.0685) loss_adv_P6_CON_dt: 0.0695 (0.0693) loss_adv_P5_CON_dt: 0.0700 (0.0701) loss_adv_P4_CON_dt: 0.0692 (0.0693) loss_adv_P3_CON_dt: 0.0708 (0.0706) time: 2.9881 (3.0192) data: 0.0089 (0.0467) lr_backbone: 0.000833 lr_middle_head: 0.000833 lr_fcos: 0.000833 lr_dis: 0.000833 max mem: 6491
2024-06-30 15:09:22,062 fcos_core.trainer INFO: eta: 2 days, 18:42:46 iter: 80 loss_gs: 3.9013 (4.4561) node_loss_gs: 1.2660 (1.6021) act_loss_gs: 0.0645 (0.1423) loss_cls_gs: 0.8427 (0.7446) loss_reg_gs: 0.9688 (1.3060) loss_centerness_gs: 0.6554 (0.6611) loss_ds: 0.3452 (0.3456) zeros: 0.0000 (0.0000) loss_adv_P7_CON_ds: 0.0700 (0.0702) loss_adv_P6_CON_ds: 0.0690 (0.0693) loss_adv_P5_CON_ds: 0.0687 (0.0686) loss_adv_P4_CON_ds: 0.0693 (0.0693) loss_adv_P3_CON_ds: 0.0682 (0.0681) loss_dt: 0.3482 (0.3479) zero_gt: 0.0000 (0.0000) loss_adv_P7_CON_dt: 0.0688 (0.0685) loss_adv_P6_CON_dt: 0.0697 (0.0694) loss_adv_P5_CON_dt: 0.0699 (0.0701) loss_adv_P4_CON_dt: 0.0693 (0.0693) loss_adv_P3_CON_dt: 0.0705 (0.0705) time: 2.9622 (3.0051) data: 0.0085 (0.0396) lr_backbone: 0.000833 lr_middle_head: 0.000833 lr_fcos: 0.000833 lr_dis: 0.000833 max mem: 6491
2024-06-30 15:10:21,933 fcos_core.trainer INFO: eta: 2 days, 18:38:41 iter: 100 loss_gs: 3.5796 (4.2845) node_loss_gs: 1.2510 (1.5350) act_loss_gs: 0.0591 (0.1266) loss_cls_gs: 0.6202 (0.7240) loss_reg_gs: 0.9625 (1.2387) loss_centerness_gs: 0.6580 (0.6602) loss_ds: 0.3446 (0.3454) zeros: 0.0000 (0.0000) loss_adv_P7_CON_ds: 0.0699 (0.0701) loss_adv_P6_CON_ds: 0.0688 (0.0692) loss_adv_P5_CON_ds: 0.0687 (0.0686) loss_adv_P4_CON_ds: 0.0689 (0.0692) loss_adv_P3_CON_ds: 0.0684 (0.0682) loss_dt: 0.3485 (0.3480) zero_gt: 0.0000 (0.0000) loss_adv_P7_CON_dt: 0.0688 (0.0686) loss_adv_P6_CON_dt: 0.0698 (0.0695) loss_adv_P5_CON_dt: 0.0699 (0.0701) loss_adv_P4_CON_dt: 0.0696 (0.0694) loss_adv_P3_CON_dt: 0.0702 (0.0705) time: 3.0099 (3.0028) data: 0.0077 (0.0355) lr_backbone: 0.000833 lr_middle_head: 0.000833 lr_fcos: 0.000833 lr_dis: 0.000833 max mem: 6491
2024-06-30 15:10:21,933 fcos_core.inference INFO: Start evaluation on ('cityscapes_foggy_val_cocostyle',) dataset(500 images).
100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 125/125 [01:13<00:00, 1.70it/s]
2024-06-30 15:11:35,624 fcos_core.inference INFO: Preparing results for COCO format
2024-06-30 15:11:35,624 fcos_core.inference INFO: Preparing bbox results
2024-06-30 15:11:36,768 fcos_core.inference INFO: Evaluating predictions
Loading and preparing results...
DONE (t=1.27s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type bbox
DONE (t=12.31s).
Accumulating evaluation results...
DONE (t=0.59s).
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.001
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.004
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.003
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.009
Maximum f-measures for classes:
[0.0, 0.019636301545291557, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]
Score thresholds for classes (used in demos for visualization purposes):
[0.0, 0.23027010262012482, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]
2024-06-30 15:11:52,272 fcos_core.inference INFO: OrderedDict([('bbox', OrderedDict([('AP', 5.6819832519004756e-05), ('AP50', 0.0003043063231258932), ('AP75', 2.225942018662298e-06), ('APs', 0.0003712871287128713), ('APm', 2.2652345072354306e-05), ('APl', 0.00036908724346504764)]))])
from sigma.
Related Issues (20)
- Unknown CUDA arch (8.6) or GPU not supported?
- Random seeds are used for training HOT 16
- Some Random Thoughts HOT 2
- Question about pseudo label and category mismatch. HOT 2
- 属性错误 HOT 2
- Sim10k's ImageSets HOT 2
- Visualization HOT 5
- source-only 训练,低mAP HOT 1
- RuntimeError: Not compiled with GPU support HOT 5
- How to tune hyperparameters for custom datasets? HOT 1
- Missing annotation files for Pascal Voc based settings HOT 3
- Question about VOC2Watercolor & Comic HOT 4
- yaml文件问题 HOT 3
- About iterative_test, I have test the traning procedure with iteration%100=0 and after 60000 start iteration%100=0 validation. Strange tihing that without iterative val the loss is different, whereas if with iterative val the loss is same. HOT 4
- T-SNE可视化 HOT 1
- source only
- 准确率和召回率的计算有接口吗 HOT 1
- A problem when running ‘python setup.py build develop’. HOT 2
- VOC HOT 2
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.
from sigma.