chenhongyiyang/gpvit

[ICLR 2023 Spotlight] GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation

Hi there 👋

I am a PhD student at the University of Edinburgh. I am currently working on computer vision problems. 👀

gpvit's Issues

[Invitation] Contribute GPViT to the upgraded MMClassification.

Hi, dear authors.

Thanks for the amazing work.

We have released the OpenMMLab 2.0 framework, and release the new version of MMClassification

We also introduce the new features in this blog.

• https://zhuanlan.zhihu.com/p/573317958

We sincerely invite you to contribute the GPViT to the upgraded MMClassification. The v1.0.0 will be released at the end of this year. We are happy to provide help if needed.

MMClassification Team.

The model files in ImageNet-1k Classification are mismatched

Hello, Amazing for your excellent work!

The model files uploaded in ImageNet-1k Classification table seem mismatched, the GPViT-L2 model is gpvit_l3_in1k_300e.pth; the GPViT-L3 and GPViT-L4 model are both gpvit_l4_in1k_400e.pth.

Thank you for your nice work！

downstream task

Hello. I have a question while re-implementing your paper.

For command 'zsh tools/dist_train.sh configs/gpvit/mask_rcnn/gpvit_l1_maskrcnn_1x.py 16', Does 16 represent the number of gpu? It has been confirmed that tools/dist_train.sh use two gpu.
Should I modify 16 to 2 to use 2 gpu? Do I not need to modify other hyperparameters?

Welcome update to OpenMMLab 2.0

Welcome update to OpenMMLab 2.0

I am Vansin, the technical operator of OpenMMLab. In September of last year, we announced the release of OpenMMLab 2.0 at the World Artificial Intelligence Conference in Shanghai. We invite you to upgrade your algorithm library to OpenMMLab 2.0 using MMEngine, which can be used for both research and commercial purposes. If you have any questions, please feel free to join us on the OpenMMLab Discord at https://discord.gg/A9dCpjHPfE or add me on WeChat (ID: van-sin) and I will invite you to the OpenMMLab WeChat group.

Here are the OpenMMLab 2.0 repos branches:

	OpenMMLab 1.0 branch	OpenMMLab 2.0 branch
MMEngine		0.x
MMCV	1.x	2.x
MMDetection	0.x 、1.x、2.x	3.x
MMAction2	0.x	1.x
MMClassification	0.x	1.x
MMSegmentation	0.x	1.x
MMDetection3D	0.x	1.x
MMEditing	0.x	1.x
MMPose	0.x	1.x
MMDeploy	0.x	1.x
MMTracking	0.x	1.x
MMOCR	0.x	1.x
MMRazor	0.x	1.x
MMSelfSup	0.x	1.x
MMRotate	0.x	1.x
MMYOLO		0.x

Attention: please create a new virtual environment for OpenMMLab 2.0.

TypeError: a bytes-like object is required, not 'NoneType'

When I run following instruction:
bash tools/dist_test.sh configs/gpvit/gpvit_l1.py gpvit_l1_in1k_300e.pth 1 --metrics accuracy

The Error occurs as following:
File "tools/test.py", line 243, in
main()
File "tools/test.py", line 200, in main
args.gpu_collect)
File "/opt/data/private/hnz/GPViT-main/mmcls/apis/test.py", line 118, in multi_gpu_test
for i, data in enumerate(data_loader):
File "/root/miniconda3/envs/vision/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 435, in next
data = self._next_data()
File "/root/miniconda3/envs/vision/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1085, in _next_data
return self._process_data(data)
File "/root/miniconda3/envs/vision/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1111, in _process_data
data.reraise()
File "/root/miniconda3/envs/vision/lib/python3.7/site-packages/torch/_utils.py", line 428, in reraise
raise self.exc_type(msg)
TypeError: Caught TypeError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/root/miniconda3/envs/vision/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 198, in _worker_loop
data = fetcher.fetch(index)
File "/root/miniconda3/envs/vision/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 "/root/miniconda3/envs/vision/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 "/opt/data/private/hnz/GPViT-main/mmcls/datasets/base_dataset.py", line 97, in getitem
return self.prepare_data(idx)
File "/opt/data/private/hnz/GPViT-main/mmcls/datasets/base_dataset.py", line 91, in prepare_data
return self.pipeline(results)
File "/opt/data/private/hnz/GPViT-main/mmcls/datasets/pipelines/compose.py", line 33, in call
data = t(data)
File "/opt/data/private/hnz/GPViT-main/mmcls/datasets/pipelines/loading.py", line 116, in call
img = mmcv.imfrombytes(img_bytes, flag=self.color_type)
File "/root/miniconda3/envs/vision/lib/python3.7/site-packages/mmcv/image/io.py", line 257, in imfrombytes
img_np = np.frombuffer(content, np.uint8)
TypeError: a bytes-like object is required, not 'NoneType'

Traceback (most recent call last):
File "/root/miniconda3/envs/vision/lib/python3.7/runpy.py", line 193, in _run_module_as_main
"main", mod_spec)
File "/root/miniconda3/envs/vision/lib/python3.7/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/root/miniconda3/envs/vision/lib/python3.7/site-packages/torch/distributed/launch.py", line 260, in
main()
File "/root/miniconda3/envs/vision/lib/python3.7/site-packages/torch/distributed/launch.py", line 256, in main
cmd=cmd)
subprocess.CalledProcessError: Command '['/root/miniconda3/envs/vision/bin/python', '-u', 'tools/test.py', '--local_rank=0', 'configs/gpvit/gpvit_l1.py', 'gpvit_l1_in1k_300e.pth', '--launcher', 'pytorch', '--metrics', 'accuracy']' returned non-zero exit status 1.

Somebody know why?