Dear Anwesh,
I am a student and I am trying to implement your code for my own use against the UBFC Dataset. I have been able to implement the pre-processing step myself however when passing the spatio temporal map inputs to the CNN I get an error stating:
RuntimeError: Given groups=1, weight of size [64, 3, 7, 7], expected input[1, 300, 25, 3] to have 3 channels, but got 300 channels instead.
I am quite confused as I thought that the dimensions for the model that I pass to the CNN are correct [1, 300, 25, 3] but the it seems like it wants shape [64, 3, 7, 7].
Dear Anwesh,
I am a student and I am trying to implement your code for my own use against the UBFC Dataset. I have been able to implement the pre-processing step myself however when passing the spatio temporal map inputs to the CNN I get an error stating:
RuntimeError: Given groups=1, weight of size [64, 3, 7, 7], expected input[1, 300, 25, 3] to have 3 channels, but got 300 channels instead.
I am quite confused as I thought that the dimensions for the model that I pass to the CNN are correct [1, 300, 25, 3] but the it seems like it wants shape [64, 3, 7, 7].