search

limaosen0 / AS-GCN

The model architecture of AS-GCN (for human action recognition)
BSD 2-Clause "Simplified" License
290 stars 71 forks source link

The accuracy is low. #6

Closed Infinite-Song closed 5 years ago

Infinite-Song commented 5 years ago

I'm really interested in the paper! I have trained this model about 100 epochs for several times. Howerver, I can't achieve the results described by the paper in NTU RGBD dataset.

  1. I have tried to train the model by using the hyper-parameters given by the yaml file, the accuracy is only about 48%. image

  2. I noticed the hyper-parameters is different from the paper, so I changed them to be the same as the paper. Finally, the accuracy is about 80%.

  3. I have also tried the older branch code committed by the author in May. The link is here: https://github.com/limaosen0/AS-GCN/tree/8efd973a8ecd37e22bb976de5cb49e1f7cb5724e But the accuracy is about 74%. I used the hyper-parameters given by the paper. The loss is about 0.38 after about 100 epochs， and it seems the loss will no longer decrease. image

Does anyone achieve the results discribed by the paper? Can anyone tell me what's wrong with my experiments? Hope your reply! Thanks!

LJ0109 commented 5 years ago

Hi,When I run the main function, I encountered this problem, how can I solve it? Thank you.

Traceback (most recent call last): File "D:/AS-GCN-master/main.py", line 22, in Processor = processors[arg.processor] KeyError: None

dangao250 commented 4 years ago

I'm really interested in the paper! I have trained this model about 100 epochs for several times. Howerver, I can't achieve the results described by the paper in NTU RGBD dataset.

  1. I have tried to train the model by using the hyper-parameters given by the yaml file, the accuracy is only about 48%. image
  2. I noticed the hyper-parameters is different from the paper, so I changed them to be the same as the paper. Finally, the accuracy is about 80%.
  3. I have also tried the older branch code committed by the author in May. The link is here: https://github.com/limaosen0/AS-GCN/tree/8efd973a8ecd37e22bb976de5cb49e1f7cb5724e But the accuracy is about 74%. I used the hyper-parameters given by the paper. The loss is about 0.38 after about 100 epochs， and it seems the loss will no longer decrease. image

Does anyone achieve the results discribed by the paper? Can anyone tell me what's wrong with my experiments? Hope your reply! Thanks!

请问你可以把你数据集分享一下可以吗 我希望你可以加我qq 我对这个方向很感兴趣

dangao250 commented 4 years ago

I'm really interested in the paper! I have trained this model about 100 epochs for several times. Howerver, I can't achieve the results described by the paper in NTU RGBD dataset.

  1. I have tried to train the model by using the hyper-parameters given by the yaml file, the accuracy is only about 48%. image
  2. I noticed the hyper-parameters is different from the paper, so I changed them to be the same as the paper. Finally, the accuracy is about 80%.
  3. I have also tried the older branch code committed by the author in May. The link is here: https://github.com/limaosen0/AS-GCN/tree/8efd973a8ecd37e22bb976de5cb49e1f7cb5724e But the accuracy is about 74%. I used the hyper-parameters given by the paper. The loss is about 0.38 after about 100 epochs， and it seems the loss will no longer decrease. image

Does anyone achieve the results discribed by the paper? Can anyone tell me what's wrong with my experiments? Hope your reply! Thanks!

How to solve this error? image

Infinite-Song commented 4 years ago

I'm really interested in the paper! I have trained this model about 100 epochs for several times. Howerver, I can't achieve the results described by the paper in NTU RGBD dataset.

  1. I have tried to train the model by using the hyper-parameters given by the yaml file, the accuracy is only about 48%. image
  2. I noticed the hyper-parameters is different from the paper, so I changed them to be the same as the paper. Finally, the accuracy is about 80%.
  3. I have also tried the older branch code committed by the author in May. The link is here: https://github.com/limaosen0/AS-GCN/tree/8efd973a8ecd37e22bb976de5cb49e1f7cb5724e But the accuracy is about 74%. I used the hyper-parameters given by the paper. The loss is about 0.38 after about 100 epochs， and it seems the loss will no longer decrease. image

Does anyone achieve the results discribed by the paper? Can anyone tell me what's wrong with my experiments? Hope your reply! Thanks!

How to solve this error? image

Comment the relevant lines directly. Here is the solution: https://github.com/limaosen0/AS-GCN/issues/2

github2016-yuan commented 2 years ago

@Infinite-Song Hello, Do you get nan err while trainning?