q5390498

can you share your training log

1

Thank you for your great work. I have tried use the code to train with custom dataset, but the trained network alway output 0, the disp_loss is quickly converged around...

``[2022-01-25 19:41:34,285] => Loading pretrained AANet: pretrained/aanet+_kitti15-2075aea1.pth [2022-01-25 19:41:34,403] => Number of trainable parameters: 8514130 [2022-01-25 19:41:34,406] => Start training... Traceback (most recent call last): File "train.py", line 246, in...

why the localNet not use global depth prediction as input

4

I am confuse that the dense depth is generated, why not use it as localnet's input? Does instead the guidance map to global depth prediction will bad to the accuracy?

the difference intrinsic parameters between train and test

1

Thank you for your great works. I found the kitti dataset has different intrinsic parameters in train set and test set. But in the test mode, it looks like only...

AssertionError: Error: Array for predictions must be between 1 and 16 (inclusive).

1

the nuscenes online eval prediction must be between 1-16, but I see the model prediction is between 0-16, how should I process the prediction 0? or I made some mistakes?...

demo_imgs前向遇到问题

1

前向时遇到这行报错，https://github.com/gangweiX/IGEV/blob/main/IGEV-Stereo/core/utils/utils.py#L68 ```text assert torch.unique(ygrid).numel() == 1 and H == 1 # This is a stereo problem AssertionError ``` 触发了这个assert，我看作者标注了`this is a stereo problem`，请问是什么问题呢？又要怎么解决呢