Open johnmaxh opened 2 years ago
It looks like when evaluating the loss in the last cell of the colab, the code uses loss = torch.nn.functional.mse_loss(rgb_predicted, target_img)
loss = torch.nn.functional.mse_loss(rgb_predicted, target_img)
But believe this should actually be loss = torch.nn.functional.mse_loss(rgb_predicted, testimg)
loss = torch.nn.functional.mse_loss(rgb_predicted, testimg)
Since we use testpose for rgb_predicted we should compare to testimg not target_img, which is just a random training sample.
testpose
rgb_predicted
testimg
target_img
It looks like when evaluating the loss in the last cell of the colab, the code uses
loss = torch.nn.functional.mse_loss(rgb_predicted, target_img)But believe this should actually be
loss = torch.nn.functional.mse_loss(rgb_predicted, testimg)Since we use
testposeforrgb_predictedwe should compare totestimgnottarget_img, which is just a random training sample.