eriklindernoren/Action-Recognition
Exploration of different solutions to action recognition in video, using neural networks implemented in PyTorch.
Python
Issues
- 3
- 1
Softmax in Model Output, then using CE Loss
#23 opened by kerrgarr - 4
Train issue
#8 opened by rebotnix - 1
how i can solve it
#22 opened by dardirz - 5
Testing performance on official UCF-101 split 1
#12 opened by pcshih - 3
latent_att not defined before.
#15 opened by shreya-cmd - 0
- 1
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]).
#20 opened by ironfactory8684 - 12
Running test_on_video.py encountered "unexpected keyword argument 'input_shape'" error
#3 opened by wangwill - 1
train.py: error: ambiguous option: --img_dim could match --img_dim_H, --img_dim_W
#19 opened by Soumi7 - 0
Terminology mistake
#18 opened by ruoshiliu - 0
Small bug fix
#17 opened by ruoshiliu - 0
- 1
Paper link for this repository!!!
#7 opened by iampartho - 1
- 1
- 4
- 0
test error
#9 opened by nicholasguimaraes - 0
- 0
Hello Mr.Linder-Norén
#1 opened by gcxkyy