deep-high-resolution-net.pytorch

deep-high-resolution-net.pytorch copied to clipboard

AttributeError: module 'torch.onnx.utils' has no attribute 'OperatorExportTypes'

4

Traceback (most recent call last): File "tools/train.py", line 223, in main() File "tools/train.py", line 111, in main writer_dict['writer'].add_graph(model, (dump_input, )) File "/home/louis/anaconda3/envs/pytorch36/lib/python3.6/site-packages/tensorboardX/writer.py", line 697, in add_graph self._get_file_writer().add_graph(graph(model, input_to_model, verbose, **kwargs))...

LouisNUST

cv2.error

4

cv2.error: OpenCV(3.4.8) /io/opencv/modules/imgproc/src/color.cpp:182: error: (-215:Assertion failed) !_src.empty() in function 'cvtColor'

IceAndSea

Thanks for such a great work. I trained HRNet-W32-C in imagenet [https://github.com/HRNet/HRNet-Image-Classification](url), got the pretrained cls model (final_state.pth.tar) which has 1956 keys. However, the pretrained model (hrnet_w32-36af842e.pth) provided by pose_hrnet_w32...

rujiewu

Hello, I trace the [training code](https://github.com/leoxiaobin/deep-high-resolution-net.pytorch/blob/master/tools/train.py) and the find that the dataloader loads the data from folder `'data/coco/'`. I'm wondering that if the data in this folder is preprocessed from...

ChongMingWei

Invalid value encountered in greater pred_mask = np.tile(np.greater(maxvals, 0.0), (1, 1, 2))

1

thanks for your greate work. I have met a problem. When I finished training the model and used the valid set for the test, the following errors appeared. Could you...

sumaliqinghua

vivva

missing pose_hrnet_w48_256x256.pth for mpii

1

Point 7 in the front page mention pose_hrnet_w48_256x256.pth is available for mpii dataset. but I could not find it neither on google drive nor on one drive

fenaux

Fix to the exception thrown while trying to access the YAML files' params as a dict (ResNet 50, 101, 152) - tested on a cloud service (AWS)

smj007

Same input but different output

1

I edit the test.py to detect a single image keypoints. I run the code several times, for the same input image, the outputs are different each time. I wonder what...

acmff22

how to i get 'keypoints_val2017_results_0.json' ??

1

To visulize coco image i don't know how to i get 'keypoints_val2017_results_0.json'

ertyu116-116