Action-Recognition

Action-Recognition copied to clipboard

Testing performance on official UCF-101 split 1

5

I can only get about 76% on UCF-101 split 1 testing dataset and the model seems overfitting... How can I fix the overfitting problem?  

pcshih

latent_att not defined before.

3

https://github.com/eriklindernoren/Action-Recognition/blob/b43ec097ab293ac8d83aac02b5addd27686ebe8c/models.py#L68

shreya-cmd

Softmax in Model Output, then using CE Loss

1

Thank you for the interesting work here. I've just encountered one issue with the code. The ConvLSTM model outputs softmax as the last layer, but then in the training script...

kerrgarr

how i can solve it

1

RuntimeError: Error(s) in loading state_dict for ConvLSTM: Missing key(s) in state_dict: "lstm.lstm.weight_ih_l0_reverse", "lstm.lstm.weight_hh_l0_reverse", "lstm.lstm.bias_ih_l0_reverse", "lstm.lstm.bias_hh_l0_reverse", "output_layers.0.weight", "output_layers.0.bias", "output_layers.1.weight", "output_layers.1.bias", "output_layers.1.running_mean", "output_layers.1.running_var", "output_layers.3.weight", "output_layers.3.bias", "attention_layer.weight", "attention_layer.bias". Unexpected key(s) in state_dict: "lstm.final.0.weight",...

dardirz

size mismatch for output_layers.3.bias: copying a param with shape torch.Size([101]) from checkpoint, the shape in current model is torch.Size([105]).

1

I get this error when I run test_on_video.py file. --------------------------------------------------------------------------- RuntimeError Traceback (most recent call last) in () ----> 1 model.load_state_dict(torch.load(checkpoint_model)) 2 model.eval() ~/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/torch/nn/modules/module.py in load_state_dict(self, state_dict, strict) 828 if...

ironfactory8684

Running test_on_video.py encountered "unexpected keyword argument 'input_shape'" error

12

python3 test_on_video.py --video_path data/UCF-101/SoccerPenalty/v_SoccerPenalty_g01_c01.avi --checkpoint_model model_checkpoints/ConvLSTM_150.pth Namespace(channels=3, checkpoint_model='model_checkpoints/ConvLSTM_150.pth', dataset_path='data/UCF-101-frames', image_dim=112, latent_dim=512, video_path='data/UCF-101/SoccerPenalty/v_SoccerPenalty_g01_c01.avi') Traceback (most recent call last): File "test_on_video.py", line 41, in model = ConvLSTM(input_shape=input_shape, num_classes=len(labels), latent_dim=opt.latent_dim) TypeError: __init__() got...

wangwill

train.py: error: ambiguous option: --img_dim could match --img_dim_H, --img_dim_W

1

I get this error when I run train.py file. ```File "/content/drive/My Drive/Action-Recognition/dataset.py", line 67, in _pad_to_length print(sequence[0]) IndexError: list index out of range ```

Soumi7

Train issue

4

This project is really interesting. I tried to train the model, but i always get a random list index out of range error during the training phase. I used torch...

rebotnix

Your model is different from ConvLSTM proposed in this paper: https://arxiv.org/abs/1506.04214, where 2D-LSTM is applied to output of each convolution layer in a CNN, usually used for pixel-level video prediction....

ruoshiliu

Thanks for sharing the repo! ```extract_frames(video_path, time_left)``` should be ```extract_frames(video_path)``` https://github.com/eriklindernoren/Action-Recognition/blob/b43ec097ab293ac8d83aac02b5addd27686ebe8c/data/extract_frames.py#L42

ruoshiliu