Yuliang (Zack) Zou

Adversarial loss

4

Thanks for sharing the source code! But I have some questions here: 1. In `adda/tools/train_adda.py` line88-103: seems that you set source domain label as 1, and target domain label as...

Compile error: 'cuda.h'

6

Not really an issue, just want to share my experience. If you are using the code in some clusters, cuda might not be installed under `/usr/local/cuda/`. In this case, in...

Data Preparation

1

For KITTI, it seems that the data preparation code only works for Eigen's split (for depth estimation), but not for Odom split (for pose estimation). I wonder if you can...

How to use the combined "tracking and mapping" mode?

4

Currently, tracking and mapping are separated. I wonder if you can also provide the code for simultaneous tracking and mapping.

In the R-FCN paper, they used the ResNet as backbone. And I found that in this repository you only implemented the VGG16 structure, is that true? Any planning for implementing...

Simultaneous Tracking and Mapping?

7

Hi, thanks for the great work. I wonder if you can provide a demo code to perform tracking (camera pose estimation) and mapping (depth estimation) simultaneously.

Add 1/2 split of VOC, update README

2

Add 1/2 split of VOC, update README

Pre-trained models for future generation?

3

It seems that the models you released only contain the the two streams part and the discriminator. Can you also share the image encoder part for future generation? (And also...

dropout behavior?

3

Hi, I am replicating the code with PyTorch. But I am not sure about the dropout behavior here. Seems that you apply dropout after all layers of the Discriminator (i.e....