IntrinsicImage

IntrinsicImage copied to clipboard

The links you provided to the MIT and MPI datasets seem to be expired. Could you provide new links, if possible? Thank you very much. It appears that the original...

Timmmza

Pytorch WHDRHingeLossPara BackPropogate question？

1

Hi, Fan! I implement a WHDRHingeLossPara class in PyTorch version, the code is followed, ```python import torch from torch.autograd import Function import math class WHDRHingeLossPara(Function): def __init__(self, delta, epsilon, device):...

FangYang970206

Why "model:training()" in test_*.lua ?

1

https://github.com/fqnchina/IntrinsicImage/blob/48fd652e317511157c06648597da121f8d4031a5/evaluation/test_IIW.lua#L30 https://github.com/fqnchina/IntrinsicImage/blob/48fd652e317511157c06648597da121f8d4031a5/evaluation/test_MIT.lua#L25 https://github.com/fqnchina/IntrinsicImage/blob/48fd652e317511157c06648597da121f8d4031a5/evaluation/test_MPI.lua#L25

Pengxiao-Wang

Hi, when i run `test_IIW.lua`, i met some problems as following: ``` path/nn/CAddTable.lua:16: bad argument #2 to 'add' (sizes do not match at path/torch/extra/cutorch/lib/THC/generated/../generic/THCTensorMathPointwise.cu:217) stack traceback: [C]: in function 'add'...

eugenelyj

Hi @fqnchina One technical question in case that you know, once I have the reflectance image, RGB [0-255], how to transform it to the corresponding allbedo values image map, [0-1]?...

ttsesm