class ResNetnnModule def __init__self block n_blocks drop_rate=00 dropblock_size=5 max_pool=True superResNet self__init__ selfinplanes = 3 selflayer1 = self_make_layerblock n_b

The error message suggests that the kernel size of the convolutional layer is larger than the size of the input. This can happen when the input image size is too small for the given configuration of the network.

To resolve this issue, you can either increase the size of the input image or reduce the kernel size of the convolutional layer.