logit form is the raw outputs of a model.
- Most common deep learning and PyTorch issues
- Wrong datatyps - our model expects torch.float32 where our original custom image was uint8.
- Wrong device - our model was on the target device (in our case, the GPU) whereas our target data hadn't been moved to the target device yet.
- Wrong shape - our model expected an input image of shape [N, C, H, W] or [batch_size, color_channels, height, width] whereas our custom image tensor was of shape [color_channels, height, width].