I’m new to convolutional neural network and machine learning in general, so sorry in advance if my question is really straighforward, but I have searched for a while without getting a solution to fix it. For a semantic segmentation task, I am pre-training a U-Net model of 4 convolution blocks in keras with a dataset whose patches have input_shape = (128,128,3). Then, I need to train this same model, but with a new dataset (input_shape=(128,128,5)). So far, I think I’ve managed to apply the convolution necessary for the U-Net model to accept tensors from 5 channels. I’ve saved the model with the weights in an h5 file. However, I got the error “keras load_weights() ValueError: Layer count mismatch when loading weights from file. Model expected 4 layers, found 23 saved layers” at the line indicate in bold in my second code block.