search

zyf12389 / GC-Net

gc-net for stereo matching by using pytorch
108 stars 20 forks source link

The result doesn't work well in my own data #2

Closed fjordyo0707 closed 5 years ago

fjordyo0707 commented 5 years ago

Hi, Thank you for releasing the code. I have tried your code, but only trained the flyingthing3D dataset. It all looks well on training and testing on flyingthing3D. However, when I tried on my own dataset which is similar to flyingthing, the result is a total mess up. I mean that even can't be recognized as a disparity map.

This is my own data 0001 0001

Below is my own data's GT and disp test_gt test_result And it is the test data in flyingthing(GT and disp) train_gt train_result

I can't figure out what's wrong with my result. Is it possible that I only train for 5 epoch? or something other like lighting ? BTW, is it possible to release your pretrained model to let me check with it?

Thank you

fjordyo0707 commented 5 years ago

I have preprocessed my input image, seems they need to apply histogram distribution