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
I want to classify images where the features (channels) represent each time step. So, the input to TCN would have input_shape=(None, timesteps, height, width). The idea here is to incorporate spatial and temporal information for classification at the same time.
Is there a possibility I can modify TCN to use it as a ConvLSTM2D layer?
The text was updated successfully, but these errors were encountered:
@Vishu26 you can't do it with TCN unless if you reshape your input to (None, timesteps, height * width). Which might be perfectly fine in terms of performance and accuracy.
I want to classify images where the features (channels) represent each time step. So, the input to TCN would have
input_shape=(None, timesteps, height, width)
. The idea here is to incorporate spatial and temporal information for classification at the same time.Is there a possibility I can modify TCN to use it as a ConvLSTM2D layer?
The text was updated successfully, but these errors were encountered: