ReekiLee

@Yuliang-Zou @isheetajha @shujonnaha Hi, sorry to bother you guys. I have the same problem, after training the predicted depth map is all white. And I also got the test error...

> @Yuliang-Zou @isheetajha @shujonnaha Hi, sorry to bother you guys. I have the same problem, after training the predicted depth map is all white. And I also got the test...

@yoryory Same with me. Have you solved it?

Hello， @simonmeister @yoryory I solved the compilation problem in TF1.15+CUDA10.0. Hope my experience could help you. The error I met is like this: backward_warp_op.cu.cc:8:53: fatal error: tensorflow/core/util/**cuda_kernel_helper.h**: No such file...

> I am sorry to bother you. When I run: "python3 -m unittest discover -s tests/", the VOC dataset works fine, but when I use my own dataset (also in...

@AlexeyAB Hello, 1. Does -quantized work only in the yolo2_light repo? 2. What'more, I found whenever I ran with -quantized or without it, the prediction time always equals to 0.00000...

hello, have u solved it now? cause i received it too...

> hello, have u solved it now? cause i received it too... > > This code is written in Python2. > I finally used this repo: https://github.com/oarriaga/face_classification Thanks !! but...

Hi @kamiLight , when the input is: pose_inputs = [pose_feats[-1], pose_feats[0]] the output: axisangle, translation = self.models["pose"](pose_inputs) there are only one pair frames (-1, 1), but get a 2 channel...