search

ShirleyMaxx / VirtualMarker

[CVPR 2023] Offical Pytorch implementation of "3D Human Mesh Estimation from Virtual Markers"
Apache License 2.0
257 stars 27 forks source link

human36d Dataset preprocessing issues #27

Closed xiaoTan12 closed 6 months ago

xiaoTan12 commented 7 months ago 
I would like to ask whether the human36d data set has been processed by toolbox or is the original image. How do you preprocess the images?
Because I encountered the following problem：

[ WARN:0@168.570] global loadsave.cpp:248 findDecoder imread_('./data/Human36M/images/s_07_act_16_subact_02_ca_01/s_07_act_16_subact_02_ca_01_000376.jpg'): can't open/read file: check file path/integrity main(args) File "main/main.py", line 94, in main n_iters_total_train = trainer.train(epoch, n_iters_total_train, master) File "/data/tx/VirtualMarker/virtualmarker/core/function.py", line 52, in train for i, meta in enumerate(batch_generator): File "/data/tx/Anaconda3/envs/pytorch/lib/python3.8/site-packages/tqdm/std.py", line 1181, in iter for obj in iterable: File "/data/tx/Anaconda3/envs/pytorch/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 630, in next data = self._next_data() File "/data/tx/Anaconda3/envs/pytorch/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1345, in _next_data return self._process_data(data) File "/data/tx/Anaconda3/envs/pytorch/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1371, in _process_data data.reraise() File "/data/tx/Anaconda3/envs/pytorch/lib/python3.8/site-packages/torch/_utils.py", line 694, in reraise raise exception TypeError: Caught TypeError in DataLoader worker process 0. Original Traceback (most recent call last): File "/data/tx/Anaconda3/envs/pytorch/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 308, in _worker_loop data = fetcher.fetch(index) File "/data/tx/Anaconda3/envs/pytorch/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 51, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/data/tx/Anaconda3/envs/pytorch/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 51, in data = [self.dataset[idx] for idx in possibly_batched_index] File "/data/tx/VirtualMarker/virtualmarker/dataset/multiple_datasets.py", line 26, in getitem return self.dbs[db_idx][data_idx] File "/data/tx/VirtualMarker/virtualmarker/dataset/human36m.py", line 100, in getitem return super().getitem(idx) File "/data/tx/VirtualMarker/virtualmarker/dataset/joints_dataset.py", line 182, in getitem img = load_img(img_path) File "/data/tx/VirtualMarker/virtualmarker/utils/preprocessing.py", line 11, in load_img img = cv2.imread(path, cv2.IMREAD_COLOR | cv2.IMREAD_IGNORE_ORIENTATION)[:,:,::-1] TypeError: 'NoneType' object is not subscriptable I would be very grateful if you could reply to me

ShirleyMaxx commented 7 months ago

We download and unzip to get the H3.6M images from I2L-MeshNet.