Jianzhong He

about the conv6_gather, and conv6_1_gather

1

i want to know what type is the conv6_gather and label_gather and conv6_gather in the training model? can anybody help, thanks very much?

A little bug in test script

1

Hi, when the length of dataset cannot be divided by the batch_size, then the origin code below https://github.com/uber-research/UPSNet/blob/aa8434e5a721ed217849607815304f68dfd7720a/upsnet/upsnet_end2end_test.py#L236 would cause ` cannot pin 'torch.cuda.FloatTensor' only CPU memory can be pinned...

I training on the NYUDv2 by changing the path to NYUD, but the loss become to nan just at the 20 iterations? I want to how to train NYUDv2, is...

about the input label

1

hello, i have show the input image and label, i found that some image if it's label/255, which is all set to be zero for that image, but there is...

In VGG, the first connected layer is 4096 7x7 filters, how to adapt these param to 3x3 1024 or 4x4 4096? Is it just copy parameters in order and remove...

Hi, @Luodian I have download the code and found that cyclegan_gta_synthia2cityscapes.sh and cyclegan_synthia2cityscapes are the same. Then i want to use the script of GTA5, however the initial model weights...