langlandslin / actclr Goto Github PK
View Code? Open in Web Editor NEWLicense: MIT License
License: MIT License
Hello, the fifth formula in the paper shows that the channel dimensions are weighted and summed, but it is not reflected in the code but is averaged. Can you tell me why this is so? cam = F.relu(cam.mean(dim=1, keepdim=True)) / (1e-8)
when i input “CUDA_VISIBLE_DEVICES=0 python -m torch.distributed.run --nproc_per_node=1 ActCLR-main/main.py pretrain_actclr -c ActCLR-main/config/ntu60/pretext/pretext_actclr_xview_joint.yaml”
it outputs:Traceback (most recent call last):
File "ActCLR-main/main.py", line 55, in
p = Processor(sys_argv)
NameError: name 'sys_argv' is not defined
could you help me to solve this problem,please?
by the way,the main.py is same as you.
Sorry to bother you again, my pretext is always around 77%, the ntu60_xview_joint.pt in the released_model used, the data is action_dataset/ntu60_frame50/xview/train_position.npy,the environment is installed according to the required content, please where do I need to change to improve
hi , ModuleNotFoundError: No module named 'processor.linear_evaluation'
Can you help me take a look at this issue? thankyou! @LanglandsLin
Hello, in which part of the code is the threshold you mentioned in your paper?
“The actionlet region is the area where the value of the generated actionlet Aitv exceeds a certain threshold, while the non-actionlet region is the remaining part.”
Hello, I followed your instructions to further implement the training of ActCLR on the pre-trained weights provided by AimCLR. However, the linear evaluation results I obtained are very different from those reported (more than 2%) in joint, bone, motion and 3s. I would like to politely ask you about possible solutions. Did you not directly use the model released by AimCLR, but retrained it yourself?
Sorry to bother you, I have a question.
The accuracy of NTU60's xview is 86.79 in the paper or 87.16 in skeleton recognition.
Many thanks for your time and consideration.
Hello, using the Data in Data Preparation and the steps in Unsupervised Pre-Training, the ActCLR-joint was less than 86.7% accurate using EPOCH350 in work. PT as a weight, can you tell me exactly how to improve the accuracy
Hello, I would like to ask how to get the samples with missing skeletons.txt in the pku part1 gendata.py?
Traceback (most recent call last):
File "main.py", line 67, in
p.start(int(os.environ["LOCAL_RANK"]))
File "/root/autodl-tmp/ActCLR/processor/processor.py", line 238, in start
self.train(epoch + 1)
File "/root/autodl-tmp/ActCLR/processor/pretrain_actclr.py", line 83, in train
loss = self.model(data1, data2, data3, data4, epoch=epoch)
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/parallel/distributed.py", line 963, in forward
output = self.module(*inputs[0], **kwargs[0])
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "/root/autodl-tmp/ActCLR/net/actclr.py", line 342, in forward
k = k * 0.5 + ks * 0.5
RuntimeError: The size of tensor a (25) must match the size of tensor b (128) at non-singleton dimension 3
0%| | 0/73 [00:02<?, ?it/s]
Traceback (most recent call last):
File "main.py", line 67, in
p.start(int(os.environ["LOCAL_RANK"]))
File "/root/autodl-tmp/ActCLR/processor/processor.py", line 238, in start
self.train(epoch + 1)
File "/root/autodl-tmp/ActCLR/processor/pretrain_actclr.py", line 83, in train
loss = self.model(data1, data2, data3, data4, epoch=epoch)
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/parallel/distributed.py", line 963, in forward
output = self.module(*inputs[0], **kwargs[0])
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "/root/autodl-tmp/ActCLR/net/actclr.py", line 342, in forward
k = k * 0.5 + ks * 0.5
RuntimeError: The size of tensor a (25) must match the size of tensor b (128) at non-singleton dimension 3
0%| | 0/73 [00:02<?, ?it/s]
Traceback (most recent call last):
File "main.py", line 67, in
p.start(int(os.environ["LOCAL_RANK"]))
File "/root/autodl-tmp/ActCLR/processor/processor.py", line 238, in start
self.train(epoch + 1)
File "/root/autodl-tmp/ActCLR/processor/pretrain_actclr.py", line 83, in train
loss = self.model(data1, data2, data3, data4, epoch=epoch)
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/parallel/distributed.py", line 963, in forward
output = self.module(*inputs[0], **kwargs[0])
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "/root/autodl-tmp/ActCLR/net/actclr.py", line 342, in forward
k = k * 0.5 + ks * 0.5
RuntimeError: The size of tensor a (25) must match the size of tensor b (128) at non-singleton dimension 3
0%| | 0/73 [00:02<?, ?it/s]
Traceback (most recent call last):
File "main.py", line 67, in
p.start(int(os.environ["LOCAL_RANK"]))
File "/root/autodl-tmp/ActCLR/processor/processor.py", line 238, in start
self.train(epoch + 1)
File "/root/autodl-tmp/ActCLR/processor/pretrain_actclr.py", line 83, in train
loss = self.model(data1, data2, data3, data4, epoch=epoch)
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/parallel/distributed.py", line 963, in forward
output = self.module(*inputs[0], **kwargs[0])
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "/root/autodl-tmp/ActCLR/net/actclr.py", line 342, in forward
k = k * 0.5 + ks * 0.5
RuntimeError: The size of tensor a (25) must match the size of tensor b (128) at non-singleton dimension 3
ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 47381) of binary: /root/miniconda3/bin/python
Traceback (most recent call last):
File "/root/miniconda3/bin/torchrun", line 8, in
sys.exit(main())
File "/root/miniconda3/lib/python3.8/site-packages/torch/distributed/elastic/multiprocessing/errors/init.py", line 345, in wrapper
return f(*args, **kwargs)
File "/root/miniconda3/lib/python3.8/site-packages/torch/distributed/run.py", line 724, in main
run(args)
File "/root/miniconda3/lib/python3.8/site-packages/torch/distributed/run.py", line 715, in run
elastic_launch(
File "/root/miniconda3/lib/python3.8/site-packages/torch/distributed/launcher/api.py", line 131, in call
return launch_agent(self._config, self._entrypoint, list(args))
File "/root/miniconda3/lib/python3.8/site-packages/torch/distributed/launcher/api.py", line 245, in launch_agent
raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:
Failures:
[1]:
time : 2023-09-15_20:09:17
host : autodl-container-ecb611b052-9dd65de2
rank : 1 (local_rank: 1)
exitcode : 1 (pid: 47382)
error_file: <N/A>
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
[2]:
time : 2023-09-15_20:09:17
host : autodl-container-ecb611b052-9dd65de2
rank : 2 (local_rank: 2)
exitcode : 1 (pid: 47383)
error_file: <N/A>
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
[3]:
time : 2023-09-15_20:09:17
host : autodl-container-ecb611b052-9dd65de2
rank : 3 (local_rank: 3)
exitcode : 1 (pid: 47384)
error_file: <N/A>
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
Root Cause (first observed failure):
[0]:
time : 2023-09-15_20:09:17
host : autodl-container-ecb611b052-9dd65de2
rank : 0 (local_rank: 0)
exitcode : 1 (pid: 47381)
error_file: <N/A>
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
Traceback (most recent call last):
File "main.py", line 65, in
p.start(int(os.environ["LOCAL_RANK"]))
File "/root/autodl-tmp/Project/ActCLR/processor/processor.py", line 201, in start
self.load_weights()
File "/root/autodl-tmp/Project/ActCLR/processor/io.py", line 72, in load_weights
self.model = self.io.load_weights(self.model, self.arg.weights,
TypeError: load_weights() takes from 3 to 4 positional arguments but 5 were given
Dear Professor:
I encountered this error when running the training code, how should I solve it? Perhaps the configuration file parameters need to be modified.
Thank you for your reply.
I don't have any questions and I'm sorry for entering the wrong information.
Hi,
I encountered this issue whle trying to debug the main.py program. Can you help me take a look? I don't know how to add this processor.
Traceback (most recent call last):
File "/home/zlq/pycharm-professional-2023.1.3/pycharm-2023.1.3/plugins/python/helpers/pydev/pydevd.py", line 1496, in _exec
pydev_imports.execfile(file, globals, locals) # execute the script
File "/home/zlq/pycharm-professional-2023.1.3/pycharm-2023.1.3/plugins/python/helpers/pydev/_pydev_imps/_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "/home/zlq/project/RVTCLR-main/main.py", line 49, in
Processor = processors[arg.processor]
KeyError: None
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.