search

Arthur151 / ROMP

Monocular, One-stage, Regression of Multiple 3D People and their 3D positions & trajectories in camera & global coordinates. ROMP[ICCV21], BEV[CVPR22], TRACE[CVPR2023]
https://www.yusun.work/
Apache License 2.0
1.31k stars 227 forks source link

EVAL CMU dataset #489

Open neverstoplearn opened 9 months ago

neverstoplearn commented 9 months ago

INFO:root:Training all layers. Initialization finished! INFO:root:gathering single image datasets. INFO:root:CMU Panoptic dataset total 9600 samples, loading test split Traceback (most recent call last): File "/xxx/miniconda3/envs/torch10/lib/python3.9/runpy.py", line 197, in _run_module_as_main return _run_code(code, main_globals, None, File "/xxx/miniconda3/envs/torch10/lib/python3.9/runpy.py", line 87, in _run_code exec(code, run_globals) File "/xxx/ROMP/romp/test.py", line 204, in main() File "/xxx/ROMP/romp/test.py", line 195, in main demo.test_cmu_panoptic() File "/xxx/ROMP/romp/test.py", line 53, in test_cmu_panoptic for test_iter,meta_data in enumerate(data_loader): File "/xxx/miniconda3/envs/torch10/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 521, in next data = self._next_data() File "/xxx/miniconda3/envs/torch10/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 561, in _next_data data = self._dataset_fetcher.fetch(index) # may raise StopIteration File "/xxx/miniconda3/envs/torch10/lib/python3.9/site-packages/torch/utils/data/_utils/fetch.py", line 49, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/xxx/miniconda3/envs/torch10/lib/python3.9/site-packages/torch/utils/data/_utils/fetch.py", line 49, in data = [self.dataset[idx] for idx in possibly_batched_index] File "/xxx/ROMP/romp/lib/models/../dataset/mixed_dataset.py", line 101, in getitem return self.dataset[index] File "/xxx/ROMP/romp/lib/models/../dataset/image_base.py", line 487, in getitem return self.get_item_single_frame(index) File "/xxx/ROMP/romp/lib/models/../dataset/image_base.py", line 117, in get_item_single_frame kp3d, valid_masks[:,1] = self.process_kp3ds(info['kp3ds'], used_person_inds, \ File "/xxx/ROMP/romp/lib/models/../dataset/image_base.py", line 359, in process_kp3ds kp3d_processed[inds] = kp3d ValueError: could not broadcast input array from shape (17,3) into shape (54,3)

hwo to fix it?

neverstoplearn commented 9 months ago

AttributeError: 'Namespace' object has no attribute 'smpl_J_reg_h37m_path'

@Arthur151 where I can got this file?