Xingang Pan
Xingang Pan
@wfchenwf I am not able to diagnose this issue given limited information, but you may refer to this repo: https://github.com/michuanhaohao/reid-strong-baseline, where they obtain promising results in person reID.
@Luoxd1996 You may check this tutorial: https://pytorch.org/tutorials/beginner/saving_loading_models.html. In our code, you can use '--model_weight' option to set the pretrained model. The pretrained models are not compressed files and do not...
@ZHUXUHAN We haven't train senet50 yet. You could train one using our code by yourself.
@vd001 I may not be able to answer your question since I haven't try IBN-Net without scale layers. In pytorch the scale layer does not interfere convergence. You may have...
@gittigxuy To train bdd100k, you'd better use this repo: https://github.com/hszhao/PSANet
@aspandey2021 Hi, the data and models in this project are for academic research purpose only. Using a pretrained model on the Culane dataset for commercial purposes is not allowed. Thanks.
@hustcc19860606 I am not very familiar with the tensorflow version, maybe you can open an issue under https://github.com/cardwing/Codes-for-Lane-Detection? But I think you still need to get curve lines from probability...
@HejhGitHub 不用去逆透视。
@HejhGitHub 我们就是直接拟合的