@xiaomengyc
Hi, the whole framework adopts modified Inception v3 as the backbone, but why the weights of pre-trained VGG-16 is restored in the training command line here?
I suppose the correct model path is "~/.torch/models/inception_v3_google-1a9a5a14.pth"?
@xiaomengyc Hi, the whole framework adopts modified Inception v3 as the backbone, but why the weights of pre-trained VGG-16 is restored in the training command line here? I suppose the correct model path is "~/.torch/models/inception_v3_google-1a9a5a14.pth"?