Closed lisaner000 closed 6 months ago
I guess there is something wrong with "insta_train_db.h5". Do you download it from VIBE? And the training labels are from TCMR and PyMAF(EFT labels), you should download them first. And NOTE if you want to reproduce STAF, there are lots of codes about loading data needing to be changed. Because I used to extract features and save them, then use the features as input during training. But it will cost huge storage space. So I suggest you change the codes in "dataset".py, and change self.generateor and related codes in trainer.py.
Epoch 1/45Traceback (most recent call last): File "train.py", line 142, in
main(cfg)
File "train.py", line 133, in main
debug_freq=cfg.DEBUG_FREQ,
File "/root/autodl-tmp/STAF-main/lib/core/trainer.py", line 342, in fit
self.train()
File "/root/autodl-tmp/STAF-main/lib/core/trainer.py", line 149, in train
target_2d = next(self.train_2d_iter)
File "/root/miniconda3/envs/yzy_staf/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 363, in next
data = self._next_data()
File "/root/miniconda3/envs/yzy_staf/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 989, in _next_data
return self._process_data(data)
File "/root/miniconda3/envs/yzy_staf/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1014, in _process_data
data.reraise()
File "/root/miniconda3/envs/yzy_staf/lib/python3.7/site-packages/torch/_utils.py", line 395, in reraise
raise self.exc_type(msg)
ValueError: Caught ValueError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/root/miniconda3/envs/yzy_staf/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 185, in _worker_loop
data = fetcher.fetch(index)
File "/root/miniconda3/envs/yzy_staf/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/root/miniconda3/envs/yzy_staf/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/root/miniconda3/envs/yzy_staf/lib/python3.7/site-packages/torch/utils/data/dataset.py", line 207, in getitem
return self.datasets[dataset_idx][sample_idx]
File "/root/autodl-tmp/STAF-main/lib/dataset/insta.py", line 59, in getitem
return self.get_single_item(index)
File "/root/autodl-tmp/STAF-main/lib/dataset/insta.py", line 70, in get_single_item
kp_2d = self.get_sequence(start_index, end_index, self.db['joints2D'])
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "/root/miniconda3/envs/yzy_staf/lib/python3.7/site-packages/h5py/_hl/group.py", line 264, in getitem
oid = h5o.open(self.id, self._e(name), lapl=self._lapl)
File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py/h5o.pyx", line 190, in h5py.h5o.open
ValueError: Not a location (invalid object ID)
About this error, I can't solve it. Can you give me some advice?