How to use v1.0-mini dataset.

[HSIN-KUANG]

Nice work!!! My PC doestn't have enough memory, I tried to modified the default dataset, but still has below error.

So Can you tell me how to use v1.0-mini dataset. Thank you！！！

[TonyPeng-2018]

Same Question.

[TonyPeng-2018]

@GenoWong In the create_data.py, you can use version to change the dataset you wanna use.

[yudefu]

Same Question.

你好，你跑成功训练stage1或者测试那个例子了吗

[lzf18]

准备数据的时候，把UniAD/tools/uniad_create_data.sh脚本里边的--version参数改成v1.0-mini，生成相应的nuscenes_infos_temporal_{train/val}.pkl文件之后再用评估脚本

[yudefu]

准备数据的时候，把UniAD/tools/uniad_create_data.sh脚本里边的--version参数改成v1.0-mini，生成相应的nuscenes_infos_temporal_{train/val}.pkl文件之后再用评估脚本

你好，你的意思是不能直接运行：./tools/uniad_dist_eval.sh ./projects/configs/stage1_track_map/base_track_map.py ./ckpts/uniad_base_track_map.pth NUM_GPUS 我上周跑的最后的结果不对，请教你一下，是不是按照你说的操作就可以解决啦： Aggregated results: AMOTA 0.000 AMOTP 2.000 RECALL 0.000 MOTAR 0.000 GT 14556 MOTA 0.000 MOTP 2.000 MT 0 ML 6470 FAF 500.0 TP 0 FP 0 FN 101897 IDS 0 FRAG 0 TID 20.00 LGD 20.00

[lzf18]

是的，先运行uniad_create_data.sh脚本，然后运行uniad_dist_eval.sh脚本，我的结果如下： Per-class results: AMOTA AMOTP RECALL MOTAR GT MOTA MOTP MT ML FAF TP FP FN IDS FRAG TID LGD bicycle 0.279 1.379 0.268 0.909 41 0.244 0.647 1 4 4.8 11 1 30 0 00.17 1.00 bus 0.657 1.134 0.788 0.885 33 0.697 0.845 0 0 9.1 26 3 7 0 10.00 3.00 car 0.661 0.835 0.761 0.759 2188 0.576 0.564 63 17 492.6 1659 399 523 6 11 1.56 1.75 motorcy 0.483 1.274 0.540 0.901 224 0.487 0.636 1 1 24.5 121 12 103 0 14.00 4.35 pedestr 0.424 1.095 0.475 0.900 1088 0.421 0.772 19 28 78.5 509 51 571 8 71.77 2.42 trailer nan nan nan nan nan nan nan nan nan nan nan nan nan nan nan nan nan truck 0.775 0.938 0.800 1.000 95 0.800 0.634 3 1 0.0 76 0 19 0 01.33 1.67

Aggregated results: AMOTA 0.544 AMOTP 1.140 RECALL 0.633 MOTAR 0.848 GT 611 MOTA 0.550 MOTP 0.703 MT 91 ML 49 FAF 106.3 TP 2530 FP 474 FN 1117 IDS 22 FRAG 22 TID 1.60 LGD 2.37

[Siriusbz]

你好，我使用uniad_create_data.sh，修改了version=v1.0-mini，创建了两个.pkl文件，但是在测试阶段发现报错，data/nuscenes/./data/nuscenes/samples/CAM_FRONT/n008-2018-08-01-15-16-36-0400__CAM_FRONT__1533151603512404.jpg ，第一个data/nuscenes来自base_track_map.py中的data_root，不知道为什么会报这样的错，我运行full的时候，用提供的.pkl就没有问题

[yudefu]

你好，我使用uniad_create_data.sh，修改了version=v1.0-mini，创建了两个.pkl文件，但是在测试阶段发现报错，data/nuscenes/./data/nuscenes/samples/CAM_FRONT/n008-2018-08-01-15-16-36-0400__CAM_FRONT__1533151603512404.jpg ，第一个data/nuscenes来自base_track_map.py中的data_root，不知道为什么会报这样的错，我运行full的时候，用提供的.pkl就没有问题

问问题可以把错误信息贴出来，你这个错误是因为报错信息代码里面有一个join操作，给它注释掉就可以了

[zhangzhongzhong1]

File "./tools/test.py", line 261, in main() File "./tools/test.py", line 231, in main outputs = custom_multi_gpu_test(model, data_loader, args.tmpdir, File "/home/zzz/Downloads/UniAD-1.0.1/projects/mmdet3d_plugin/uniad/apis/test.py", line 88, in custom_multi_gpu_test for i, data in enumerate(data_loader): File "/home/zzz/anaconda3/envs/uniad/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 521, in next data = self._next_data() File "/home/zzz/anaconda3/envs/uniad/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1203, in _next_data return self._process_data(data) File "/home/zzz/anaconda3/envs/uniad/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1229, in _process_data data.reraise() File "/home/zzz/anaconda3/envs/uniad/lib/python3.8/site-packages/torch/_utils.py", line 425, in reraise raise self.exc_type(msg) FileNotFoundError: Caught FileNotFoundError in DataLoader worker process 0. Original Traceback (most recent call last): File "/home/zzz/anaconda3/envs/uniad/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop data = fetcher.fetch(index) File "/home/zzz/anaconda3/envs/uniad/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/zzz/anaconda3/envs/uniad/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 44, in data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/zzz/Downloads/UniAD-1.0.1/projects/mmdet3d_plugin/datasets/nuscenes_e2e_dataset.py", line 726, in getitem return self.prepare_test_data(idx) File "/home/zzz/Downloads/UniAD-1.0.1/projects/mmdet3d_plugin/datasets/nuscenes_e2e_dataset.py", line 254, in prepare_test_data example = self.pipeline(input_dict) File "/home/zzz/anaconda3/envs/uniad/lib/python3.8/site-packages/mmdet/datasets/pipelines/compose.py", line 40, in call data = t(data) File "/home/zzz/Downloads/UniAD-1.0.1/projects/mmdet3d_plugin/datasets/pipelines/loading.py", line 53, in call img = mmcv.imread(img_path, self.color_type) File "/home/zzz/anaconda3/envs/uniad/lib/python3.8/site-packages/mmcv/image/io.py", line 176, in imread check_file_exist(img_or_path, File "/home/zzz/anaconda3/envs/uniad/lib/python3.8/site-packages/mmcv/utils/path.py", line 23, in check_file_exist raise FileNotFoundError(msg_tmpl.format(filename)) FileNotFoundError: img file does not exist: data/nuscenes/v1.0-mini/./data/nuscenes/v1.0-mini/samples/CAM_FRONT/n008-2018-08-01-15-16-36-0400__CAM_FRONT__1533151603512404.jpg 你好，这个问题能帮忙看一下吗