Colorization features require grayscale inputs about midlevel-reps HOT 1 OPEN

I actually get an error when defining the model. There is a mismatch between the shape of their pre-trained weights of the first convolutional layer (64,1,7,7) with that of the architecture definition (64,3,7,7).

Should one adjust the architecture definition of the TaskonomyEncoder to have only one channel in the input conv layer, or repeat three times the weights of the first conv layer of checkpoints['state_dict'] along channel dimensions?

from midlevel-reps.