yanglei18
commented
1 year ago [ WARN:[0@8.916](mailto:0@8.916)] global loadsave.cpp:248 findDecoder imread_('../datasets/kitti/training/../../datasets/kitti/gt_database/image_2/26110_Car_0_0.jpg'): can't open/read file: check file path/integrity
其中：../datasets/kitti/training/../../datasets/kitti/gt_database/image_2/26110_Car_0_0.jpg等价于../datasets/datasets/kitti/gt_database/image_2/26110_Car_0_0.jpg
因此，实例级图块路径存在问题
[2023-09-05 20:47:28,194] monoflex.seed INFO: Using a generated random seed 26660 [2023-09-05 20:47:31,969] monoflex.augmentations INFO: Using <class 'MonoFlex.data.augmentations.augmentations.RandomHorizontallyFlip'> aug with params [0.5] [2023-09-05 20:47:31,969] monoflex.dataset INFO: Initializing KITTI train set with 3712 files loaded. [2023-09-05 20:47:32,152] monoflex.dataset INFO: Initializing KITTI val set with 3769 files loaded.
data = [self.dataset[idx] for idx in possibly_batched_index]
File "../MonoFlex/data/datasets/kitti.py", line 303, in getitem
img, P, use_bcp, embedding_annos, image_idx = self.aug_dataset[idx]
File "../MonoFlex/data/datasets/aug_dataset.py", line 213, in getitem
patch_img[patch_img_ind_1 : patch_img_ind_1 + box2d_h, patch_img_ind_0 : patch_img_ind_0 + box2d_w, :] ratio
TypeError: 'NoneType' object is not subscriptable、
[2023-09-05 20:47:32,173] monoflex.checkpointer INFO: Loading checkpoint from ../MonoFlex/output/exp1/model_moderate_best_soft.pth [2023-09-05 20:47:32,500] monoflex.checkpointer INFO: loading checkpoint from iterations 116000 [2023-09-05 20:47:32,501] monoflex.checkpointer INFO: Loading optimizer from ../MonoFlex/output/exp1/model_moderate_best_soft.pth [2023-09-05 20:47:32,663] monoflex.checkpointer INFO: Loading scheduler from ../MonoFlex/output/exp1/model_moderate_bestsoft.pth [2023-09-05 20:47:32,663] monoflex.trainer INFO: Start training
[ WARN:0@8.916] global loadsave.cpp:248 findDecoder imread('../datasets/kitti/training/../../datasets/kitti/gt_database/image_2/26110_Car_0_0.jpg'): can't open/read file: check file path/integrity Traceback (most recent call last): File "tools/plain_train_net.py", line 172, in
args=(args,), "xjtu-Super-Server" 10:14 05-9月-23 File "./engine/launch.py", line 57, in launch main_func(args) File "tools/plain_train_net.py", line 147, in main train(cfg, model, device, distributed) File "tools/plain_train_net.py", line 85, in train arguments, File "./engine/trainer.py", line 112, in do_train for data, iteration in zip(data_loader, range(start_iter, max_iter)): File "../envs/envs/monoflex/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 345, in next data = self._next_data() File "../envs/envs/monoflex/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 856, in _next_data return self._process_data(data) File "../envs/envs/monoflex/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 881, in _process_data data.reraise() File "../envs/envs/monoflex/lib/python3.7/site-packages/torch/_utils.py", line 394, in reraise raise self.exc_type(msg) TypeError: Caught TypeError in DataLoader worker process 0. Original Traceback (most recent call last): File "../envs/envs/monoflex/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop data = fetcher.fetch(index) File ../envs/envs/monoflex/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 "../envs/envs/monoflex/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in
上面是我错误的全部信息，我不知道是什么原因导致我无法读取对应路径上的图片，以至于出现了下面的错误，但是在路径‘../datasets/kitti/gt_database/image_2/26110_Car_0_0.jpg’下确实存在对应的图片，且下载后发现图片并没有损坏，这是因为路径没有化简导致的错误吗？
Above is all the information about my error. I don’t know why I can’t read the image at the corresponding path, which caused the following error. However, there is indeed a corresponding image under the path ‘…/datasets/kitti/gt_database/image_2/26110_Car_0_0.jpg’, and after downloading, I found that the image was not damaged. Is this an error caused by the path not being simplified?