search

thayral / temporal-stochastic-softmax

Code for "Temporal Stochastic Softmax for 3D CNNs", presented at WACV2021.
MIT License
0 stars 0 forks source link

The Bug of Classifier3D.py #1

Closed liangying-Ke closed 1 year ago

liangying-Ke commented 2 years ago

Hi, Thanks for your implement. But, there is a bug in the forward function of model. Because the feature dimension of model after the Linear Module will be two, you couldn't use permute to change the dimension.

Is the max_pool1d necessary? Maybe the output of Linear Module is almost the scores?

thayral commented 2 years ago

Hello,

We feed 3 dimensional feature vectors to the classifier (Time Length, Batch, Channels). The Linear modules consider this as 2-dimensional (LxB, C). It is like we use .view(L*B,C) implicitly. This is why we do permute to (B, C, L) and then pool1d on the temporal dimension L, and additional softmax pooling if we are in eval mode with long videos (as opposed to short training clips).

Do you have an actual error when running the model or just reading the code ? If you have an error can you check the dimensions of your inputs to the vgg model ? I commented in the code with the feature dimensions at each step of the model, from (B, C, L, H, W) input to (B, C) output scores. L is temporal, HxW are spatial dimensions.