You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
There are so many fc layers in both CNN encoder and RNN decoder, only one is enough. When I implement the CRNN training, I got over 70% test acc with only one fc layer in both CNN and LSTM (However, there is still a huge overfitting). When the num_fc_layers increases, the performance degrades.
Plus, BatchNorm probably contradicts with dropout, because dropout could affect the statistics of BN, BN is already a regularizer. Maybe no dropout is better.
The text was updated successfully, but these errors were encountered:
I use ResNet-18(pretrained) + LSTM and get over 80% test acc, but only 40% test acc when training ResNet-18 + LSTM from scratch. It seems that pretraining ResNet CNN encoder on ImageNet is essential.
There are so many fc layers in both CNN encoder and RNN decoder, only one is enough. When I implement the CRNN training, I got over 70% test acc with only one fc layer in both CNN and LSTM (However, there is still a huge overfitting). When the
num_fc_layers
increases, the performance degrades.Plus, BatchNorm probably contradicts with dropout, because dropout could affect the statistics of BN, BN is already a regularizer. Maybe no dropout is better.
The text was updated successfully, but these errors were encountered: