human-pose-estimation.pytorch
human-pose-estimation.pytorch copied to clipboard
Hi is it possible for you to tell me the input and output shape of the model please?
I can't run the code on windows and I also can't install Linux right now due to personal issues, I am currently just backtracking everything in your code right now trying to rewrite it so it would work for my system. I am having a hard time figuring out the input data tensor shape and the correct output shape. I have managed to recreate the model in pytorch and I assumed the input data shape for the 50 layer resnet is [B, 3, 384, 288] for coco and [B, C, 256, 256] with mpii is this correct? If not can you please tell me what the input and output tensor shapes are?