Wen Y.K.

not even a problem

5

Your code is very nice, thank you! But in the main.py, you seem to forgot import cv2 ?

Could you give me your petrained-depth-models ? I want to use it to draw some figures and I want to ask that how to make kitti depth gt image?

GT depth generation

1

Hello, may I ask how the GT depth image in your paper was generated?Kitti seems to have given only sparse depth maps, how to generate a pixel by pixel GT...

Questions about test accuracy

1

Here is your readme‘s results | Abs Rel | Sq Rel | RMSE | RMSE(log) | Acc.1 | Acc.2 | Acc.3 | |---------|--------|-------|-----------|-------|-------|-------| | 0.183 | 1.595 | 6.709 |...

inference

2

What should I do if I only want to use your code for a few images?

Depth measurement

5

 I have evaluated the depth model you gave ，why is it different? What might be wrong? My device is 1080ti and the model for the evaluation is k_depth.tar, and...

How do I pass out the object_list for each frame?Modify the post-handler?

uni_loss

5

 阅读您的代码，我发现您的uni_xy_loss的实现有一些问题，argsort不是说某个数值对应的是排序后的第几个。 举个例子 ，如果position 是 [0.1, 0.5, 0.3, 0.2, 0.4],那argsort的结果是 [0., 3., 2., 4., 1] ,而实际上您想要的是[0,4,2,1,3]，这是不同的。正确的实现可以类似于一下： target_distribution = t.arange(position.shape[0]).type_as(rela_a) / (position.shape[0] - 1) position = t.sort(position)[0] uni_loss = t.sum((a -...

about data aug

2

Do you have any code for data augmentation，I'd like to study, could I ？