Jiaxing Yan

> We don't support data-dependent shapes for plugin currently. The output shape must be able to compute from inputs' shape. what's the meaning of data-dependent shapes, could you please provide...

For faster image preprocessing, we use opencv+albumentations instead of pil+ torchvision which Monodepth2 uses, you can see datasets/mono_dataset.py for more details. And you can see [this](https://www.kaggle.com/code/yukia18/opencv-vs-pil-speed-comparisons-for-pytorch-user/notebook) experiments for speed comparison.

we haven't compared the training time between the MonoDepth2 and CADepth-Net with different encoder, but i think you can use some tools, like lineprofiler, to check the running speed for...

the axisangle of i-1^{th} frame and i^{th} frame is axisangle [:, 0], and axisangle [:, 1] is for i^{th} frame and i+1^{th} frame, so the channel of axisangle is 2...

这个问题有进展了吗，我也遇到了同样的问题，训练时间一长dataloader就要被kill掉