Zhengyang Feng

Thanks a lot for your support!

@MehdiAlilou I have never done this before. Could you share your latest culane fine-tuning config file?

ok. Let me check that when I have free GPUs later today.

@MehdiAlilou I can't use my testing env for now. But I think this config could do the finetuning, maybe try it out? [culane_finetune.zip](https://github.com/voldemortX/pytorch-auto-drive/files/9069097/culane_finetune.zip)

Unfortunately, we did not leave that functional for lane detection. You will have to do some hacking yourself. As earlier discussed in #79 . However, in your finetuning case checkpointing...

@liuYYYYYYYYy You can use it in NVIDIA's related packages. I believe there is pip inference toolkits like `tensorrt`. See https://developer.nvidia.com/tensorrt for introductions.

@liuYYYYYYYYy Currently we only provide conversion codes. However, we do have some verification codes that does inference [here](https://github.com/voldemortX/pytorch-auto-drive/blob/b8d74e524f726abe844bd09c44b014eabc4fc065/utils/tensorrt_utils.py#L69). You could use it similarly like [here](https://github.com/voldemortX/pytorch-auto-drive/blob/b8d74e524f726abe844bd09c44b014eabc4fc065/tools/to_tensorrt.py#L27). In the future, we might...

@Wakarox Check if you have the c++ OpenCV on your system?

> I am using cv2. > I commented the line 21 as the tutorial said. that is weird. you sure it is not python opencv?

@Wakarox Can you display opencv version by `pkg-config --modversion opencv` ?