Cheng Zhang

LEN, ODN, and Joint training result looks odd

5

Hi Yinyu: I tried LEN, ODN training code with batch size 32, but get the following loss curve:  It looks like the test loss stops converging soon after a...

MGNet pretraining goes wrong

15

Hi Yinyu: I tried to pretrain MGNet with `python main.py configs/mgnet.yaml --mode train` and test it with `python main.py configs/mgnet.yaml --mode test`. However, after 50 epochs of training, the learning...

Evaluation code roomlayout.m of cooperative_scene_parsing don't work on the output

3

Hi Yinyu: I followed your guide to evaluate the results using code from [cooperative_scene_parsing](https://github.com/thusiyuan/cooperative_scene_parsing). With GT downloaded and some essential changes to path settings, the roomlayout.m runs successfully on the...

I'm an undergraduate student from UESTC. And I'm working on my graduation project on this topic. In my early learning stage, I want to try retraining your net. So, I'd...

Hi Shir. Thanks for your great work and code! I am trying to reproduce the results of your paper and _Aperture Supervision for Monocular Depth Estimation_. However, the [published source...

Hi Shir: I am trying to reproduce your results. However, I noticed that not all of your code are out, especially code of training on Flowers, DSLR, KITTI, and Make3D...