JOP-Lee / READ

AAAI2023,implementation of "READ: Large-Scale Neural Scene Rendering for Autonomous Driving", the experimental results are significantly better than Nerf-based methods
https://github.com/JOP-Lee/READ-Large-Scale-Neural-Scene-Rendering-for-Autonomous-Driving
GNU General Public License v2.0
447 stars 55 forks source link

src的dataloader #52

Closed Korace0v0 closed 1 year ago

Korace0v0 commented 1 year ago

您好,我尝试用使用您的src源码里的train.py文件,但我发现 src/READ/datasets/dynamic.py 里的 inner_batch 似乎在src/READ/datasets/dynamic.py没有被定义,

        use_mesh=args.use_mesh, supersampling=args.supersampling, headless=args.headless, **args.train_dataset_args)

而这个变量在 getitem 函数里被用于数据增强 Hs = self.get_transform_crop(self.inner_batch,8)

这里是否存在一些bug呢?感谢您的帮助!

Korace0v0 commented 1 year ago

或者我是否能够避免 调用屏幕直接运行源码呢?

Korace0v0 commented 1 year ago

我直接注释掉了 self.get_transform_crop的输入,目前训练程序可以正常运行, 感谢您的工作!