Akash Goyal

@shadow111 Were you able to have a proper model for android ? @akirasosa I converted the `.h5` to `.pb` with `tf-converter.py`. The `pb` runs very well on desktop. But the...

Hi @akirasosa I have solved above issue. The model can be loaded but here's another problem : ` No Operation named [hair_recognition/input_1] in the Graph` What I could think is...

Hi @yangjie10930 @gk-vk I am facing same issue. Any help on its resolution.

@bittnt You wrote - "I have tested this under CUDA8, CUDA7.5, CUDA6.5, and CUDA6" **Can you please tell which version of cuDNN you used with CUDA8 ?** I am asking...

@bittnt I donot see anything like `crfasrnn branch`. Can you please help me with that branch.

@bittnt I worked on the `crfrnn branch` but still CUDA8 + cudNN(5/5.1/6/7) nothing worked. If it worked for you can you please share the `cudnn.hpp` file which worked for CUDA8...

That file generates image from noise, I am looking for something which can do the reverse operation. Image to Noise.

TrainA & TrainB are two different folders. Is it related to source(target) to target(source). Can you please provide any sample image that is to be placed in these folders. ?

b.resize(0) worked for me. But I am not able to release solutionChannels. Any clue ?