search

ibrahimgh25 / EL-GAN-Implementation

A pytorch implementation for the network in "EL-GAN: Embedding Loss Driven Generative Adversarial Networks for Lane Detection" by Ghafoorian et al.
MIT License
3 stars 0 forks source link

How to use the code for training on Tusimple Dataset #1

Closed wxiangxiaow closed 2 years ago

wxiangxiaow commented 2 years ago

Thanks for your great work! Could you please write a more detailed README for using Tusimple Dataset? Like how the dataset and code files should be arrange? If you had done this work, please tell me how to find. Thank you again!

ibrahimgh25 commented 2 years ago

Regarding using the Tusimple, the training_utils.dataset class defines how the dataset is loaded into pytorch. When I used the code, I downloaded the dataset from here (I believe i used images from test_set.zip). After you download the dataset, unzip it in some directory, which you'll pass to the dataset constructor. (see how the dataloaders are defined in elgan_training.py. Regarding updating the README, please confirm that the steps I shared with you work and then I could add them to the README.