ilnehc
commented
1 year ago @bithuanglq Could you check the package version to see if it is caused by https://github.com/nutonomy/nuscenes-devkit/issues/887?
Closed bithuanglq closed 1 year ago
ilnehc
commented
1 year ago @bithuanglq Could you check the package version to see if it is caused by https://github.com/nutonomy/nuscenes-devkit/issues/887?
Sorry, may I ask how to select the correct dataset and place it in the correct directory? Nuscenes dataset website: https://www.nuscenes.org/download But I don't know which one is suitable to your pre-trained model.
I have download: Full dataset (v1.0) --> Mini --> Asia Full dataset (v1.0) --> Trainval --> Metadata --> Asia CAN bus expansion --> CAN bus expansion pack --> Asia Map expansion --> Map expansion pack (v1.3) --> Asia
Then I unzip them and put them in the correct relative position: /data/sets/nuscenes/ ----- can_bus ----- maps, including .png and .json files ----- samples ----- v1.0-trainval
However, I get errors as below when I try to run evaluate.py :
Traceback (most recent call last): File "evaluate.py", line 285, in
eval(args.checkpoint, args.dataroot)
File "evaluate.py", line 80, in eval
for index, batch in enumerate(tqdm(valloader)):
File "/opt/conda/envs/stp3/lib/python3.7/site-packages/tqdm/std.py", line 1165, in iter
for obj in iterable:
File "/opt/conda/envs/stp3/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 521, in next
data = self._next_data()
File "/opt/conda/envs/stp3/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1203, in _next_data
return self._process_data(data)
File "/opt/conda/envs/stp3/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1229, in _process_data
data.reraise()
File "/opt/conda/envs/stp3/lib/python3.7/site-packages/torch/_utils.py", line 434, in reraise
raise exception
TypeError: Caught TypeError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/opt/conda/envs/stp3/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop
data = fetcher.fetch(index)
File "/opt/conda/envs/stp3/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 49, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/opt/conda/envs/stp3/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 49, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/mnt/ST-P3/stp3/datas/NuscenesData.py", line 616, in getitem
hd_map_feature = self.voxelize_hd_map(rec)
File "/mnt/ST-P3/stp3/datas/NuscenesData.py", line 463, in voxelize_hd_map
hd_features = self.nusc_maps[map_name].get_map_mask(box_coords, rot * 180 / np.pi , elements, canvas_size=canvas_size)
File "/opt/conda/envs/stp3/lib/python3.7/site-packages/nuscenes/map_expansion/map_api.py", line 375, in get_map_mask
return self.explorer.get_map_mask(patch_box, patch_angle, layer_names, canvas_size)
File "/opt/conda/envs/stp3/lib/python3.7/site-packages/nuscenes/map_expansion/map_api.py", line 839, in get_map_mask
map_mask = self.map_geom_to_mask(map_geom, local_box, canvas_size)
File "/opt/conda/envs/stp3/lib/python3.7/site-packages/nuscenes/map_expansion/map_api.py", line 788, in map_geom_to_mask
layer_mask = self._layer_geom_to_mask(layer_name, layer_geom, local_box, canvas_size)
File "/opt/conda/envs/stp3/lib/python3.7/site-packages/nuscenes/map_expansion/map_api.py", line 1744, in _layer_geom_to_mask
return self._polygon_geom_to_mask(layer_geom, local_box, layer_name, canvas_size)
File "/opt/conda/envs/stp3/lib/python3.7/site-packages/nuscenes/map_expansion/map_api.py", line 1831, in _polygon_geom_to_mask
map_mask = self.mask_for_polygons(new_polygon, map_mask)
File "/opt/conda/envs/stp3/lib/python3.7/site-packages/nuscenes/map_expansion/map_api.py", line 1764, in mask_for_polygons
exteriors = [int_coords(poly.exterior.coords) for poly in polygons]
TypeError: 'MultiPolygon' object is not iterable