🐛 Describe the bug According to the official document, nll_loss can compute case input.shape= (N, C) and target.shape= (N,), where N is batch number and C is numbert of classes, in this case ...

Inspired by vision transformers, it offers efficient image classification with fewer parameters and high performance. We developed a multi-input one-dimensional convolutional mixer (MI-1D-ConvMixer) ...