Rogersljs

Hello, have you used surroundocc for training? I used the nuscenes-mini dataset and created the dataset pkl file in tools/create-data.py, but when training, an error message [Errno 2] No such...

请问，你解决了吗？

谢谢您！经过以上修改后，在终端输入bash tools/dist_test.sh projects/configs/flashocc/flashocc-r50-M0.py work_dirs/flashocc-r50-M0/latest.pth 1 --eval ray-iou 出现了Starting Evaluation... Traceback (most recent call last): File "tools/test.py", line 290, in main() File "tools/test.py", line 286, in main print(dataset.evaluate(outputs, **eval_kwargs)) File "/home/leapting/work/2024-07-17-FlashOcc/FlashOCC/projects/mmdet3d_plugin/datasets/nuscenes_dataset_occ.py",...

就是配置文件 都一样 没关系 我改了nuscenes-dataset-occ.py的eval函数 在issue里写了发自我的 iPhone在 2024年8月12日，11:31，xzyun2011 ***@***.***> 写道： 老哥解决这个问题了吗？代码更新的是 panoptic-flashocc-r50-depth.py， Get Started里面用的是 projects/configs/flashocc/flashocc-r50.py —Reply to this email directly, view it on GitHub, or unsubscribe.You are receiving this because you...

> Thanks for your attention. We've fixed the problem, please update the code and weights. > > Best wishes. Thank you for your reply. My question has been resolved

Hello author, I also ran the code during the test phase by modifying the evaluate function method in nuscenes_dataset_occ.py. The following is the modified function information： def evaluate(self, occ_results, runner=None,...

In vis_occ.py, I also encountered the same problem, I modified the code on line 233: for i, data in tqdm(enumerate(val_loader)): with torch.no_grad(): occ_pred = model(return_loss=False, rescale=True, **data)[0] # print(f"Type of...