HOU Yuenan

I have met the same problem. My solution is to not activate tensorflow in the terminal, i.e., not use "source activate tensorflow". Just use "python pspnet.py -m pspnet101_cityscapes -i example_images/cityscapes.png...

@Vladkryvoruchko , not use tf in the terminal is just not execute "source activate tensorflow". Just use "python file_name.py -m pspnet101_cityscapes -i example_images/cityscapes.png -o example_results/cityscapes.jpg" should work.

Just use "python pspnet.py -m pspnet101_cityscapes -i example_images/cityscapes.png -o example_results/cityscapes.jpg".

I will implement both Pytorch version and TensorFlow version when I am free. However, you can just read the torch codes, then write the PyTorch / TensorFlow codes and pull...

@mengzhibin [ERFNet-CULane-PyTorch](https://github.com/cardwing/Codes-for-Lane-Detection) has been released. (It can achieve **73.1** F1-measure in CULane testing set)

@mengzhibin You are welcome. And you can add other features, e.g., SAD, to the PyTorch codes. You can obtain better performance in all benchmarks.

That site only contains the backbone model of that paper, i.e., ENet which achieves 68.8 F1-measure on CULane testing set (After a recent update the newest model can achieve 72.0...

@chenchaohui, I have not implemented VPGNet since their dataset has not been released. And you can directly list your questions in [my repo](https://github.com/cardwing/Codes-for-Lane-Detection) and I will respond to you ASAP....

@Oliver-jiang Can you share your retraining result of the searched architecture with us? Thanks a lot.

@Oliver-jiang Since RTX 2080Ti only has 11GB memory, you may have banned global pooling in ASPP. That may be the reason for the bad performance.