Closed l2009312042 closed 4 years ago
tensorFlow = 20.0 * torch.nn.functional.interpolate(input=moduleNetwork(tensorPreprocessedFirst, tensorPreprocessedSecond), size=(intHeight, intWidth), mode='bilinear', align_corners=False)
in the paper ,the author say "We scale the ground truth flow by 20 and downsample it to obtain the supervision signals at different levels.",
and " our model outputs a quarter resolution optical flow and uses bilinear interpolation to obtain the full-resolution optical flow.",
the output flow interpolation to full-resolution optical flow ,why it not multiply by 2?
I ported the official Caffe model, which multiplies by 20 as follows.
https://github.com/NVlabs/PWC-Net/blob/864d2e9fb3f60f9af99f4ea72943b1ff5d472202/Caffe/model/pwc_net_test.prototxt#L2924
For additional questions, you might want to direct your question at the authors of PWC-Net.
tensorFlow = 20.0 * torch.nn.functional.interpolate(input=moduleNetwork(tensorPreprocessedFirst, tensorPreprocessedSecond), size=(intHeight, intWidth), mode='bilinear', align_corners=False)
in the paper ,the author say "We scale the ground truth flow by 20 and downsample it to obtain the supervision signals at different levels.",
and " our model outputs a quarter resolution optical flow and uses bilinear interpolation to obtain the full-resolution optical flow.",
the output flow interpolation to full-resolution optical flow ,why it not multiply by 2?