search

Gait3D / Gait3D-Benchmark

This is the code for the paper "Gait Recognition in the Wild with Dense 3D Representations and A Benchmark. (CVPR 2022)", "Gait Recognition in the Wild with Multi-hop Temporal Switch", and "Parsing is All You Need for Accurate Gait Recognition in the Wild".
133 stars 19 forks source link

Error when test #16

Closed breeze0011 closed 1 year ago

breeze0011 commented 1 year ago

There was no probelm when I was training. But there is something wrong when I was testing. And I have no idea how to solve this.

breeze0011 commented 1 year ago

Transforming: 0%| | 0/6369 [00:00<?, ?it/s]:6: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray. Traceback (most recent call last): File "lib/main.py", line 76, in run_model(cfgs, training) File "lib/main.py", line 53, in run_model Model.run_test(model) File "/home/Gait3D/lib/modeling/base_model.py", line 501, in run_test info_dict = model.inference(rank) File "/home/Gait3D/lib/modeling/base_model.py", line 436, in inference for inputs in self.test_loader: File "/opt/anaconda3/envs/Gait3D/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 652, in next data = self._next_data() File "/opt/anaconda3/envs/Gait3D/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1347, in _next_data return self._process_data(data) File "/opt/anaconda3/envs/Gait3D/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1373, in _process_data data.reraise() File "/opt/anaconda3/envs/Gait3D/lib/python3.7/site-packages/torch/_utils.py", line 461, in reraise raise exception ValueError: Caught ValueError in DataLoader worker process 0. Original Traceback (most recent call last): File "/opt/anaconda3/envs/Gait3D/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 302, in _worker_loop data = fetcher.fetch(index) File "/opt/anaconda3/envs/Gait3D/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 52, in fetch return self.collate_fn(data) File "/home/Gait3D/lib/data/collate_fn.py", line 121, in call fras_batch = [[my_cat(k)] for k in range(feature_num)] # [f, g] File "/home/Gait3D/lib/data/collate_fn.py", line 121, in fras_batch = [[my_cat(k)] for k in range(feature_num)] # [f, g] File "/home/Gait3D/lib/data/collate_fn.py", line 120, in my_cat [fras_batch[i][k] for i in range(batch_size)], 0) File "<__array_function__ internals>", line 6, in concatenate ValueError: could not broadcast input array from shape (72,128,88) into shape (72,)

JinkaiZheng commented 1 year ago

Please put up your running command and the detailed config settings, i.e., the .yaml file.

breeze0011 commented 1 year ago

Thanks, I found the problem! I have set the plus_smpl to false. After I change it to true. Now it can run.

JinkaiZheng commented 1 year ago

That's good!