Jack Yi

per pixel acc: #Correctly_labeled_pixel/#all_pixel per class acc: #Correctly_labeled_pixel_of_class_A/#all_pixel_of_class_A they are computed by aggregating all pixels of all test imaes, rather than per image.

The codes currently only supports images of width==height. For the latter case, "--A_channels 3 --B_channels 1 " is just what you need. On 6 November 2017 at 23:59, wang5566 wrote:...

The size must be 128, 256, 512, 2^n... On 7 November 2017 at 00:51, wang5566 wrote: > Thank you for your reply. I resize my training set to the same...

Sorry, unequal width and height is not supported yet. I will try add this feature in future version. On 18 April 2018 at 07:56, xiaoshidai wrote: > Hello, I want...

> Finally, I get the correct result. > You mentioned that you got the above problem because you had not computed the Action Units of each face correctly, so I...

The links to the BlendedMVS+ and BlendedMVS++ expired too. could you please provide the new links?

> Hello, I have updated all links. Would you try again? @duxingren14 Solved, Great thanks.

Which model? the one trained on places2? On Tue, Oct 25, 2022 at 10:21 AM Shawn-Yu-1 ***@***.***> wrote: > I retrain the model for about 800000 pics of image in...

No idea what happens to your training. I think it is unreasonable to generate "random" results if the training is properly performed. Assume that a model could be overfit to...