error

[ezzatmostafa96]

loading dataset ... loading_model ... 2020-11-02 16:06:51,083 - mmaction - INFO - These parameters in pretrained checkpoint are not loaded: {'fc.weight', 'fc.bias'} 2020-11-02 16:06:51,142 - mmaction - INFO - load checkpoint from https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/recognition/tsn/tsn_r50_video_1x1x8_100e_kinetics400_rgb/tsn_r50_video_1x1x8_100e_kinetics400_rgb_20200702-568cde33.pth creating workspace directory ... Done Starting to train ... 2020-11-02 16:06:53,802 - mmaction - WARNING - The model and loaded state dict do not match exactly

size mismatch for cls_head.fc_cls.weight: copying a param with shape torch.Size([400, 2048]) from checkpoint, the shape in current model is torch.Size([13, 2048]). size mismatch for cls_head.fc_cls.bias: copying a param with shape torch.Size([400]) from checkpoint, the shape in current model is torch.Size([13]). 2020-11-02 16:06:53,805 - mmaction - INFO - Start running, host: root@5f8f50143665, work_dir: /content/work_dirs 2020-11-02 16:06:53,806 - mmaction - INFO - workflow: [('train', 1)], max: 100 epochs 2020-11-02 16:08:10,766 - mmaction - INFO - Epoch [1][10/92] lr: 1.000e-03, eta: 19:38:39, time: 7.695, data_time: 6.966, memory: 6252, top1_acc: 0.1375, top5_acc: 0.5375, loss_cls: 2.5019, loss: 2.5019, grad_norm: 9.7265 2020-11-02 16:08:51,116 - mmaction - INFO - Epoch [1][20/92] lr: 1.000e-03, eta: 14:57:22, time: 4.035, data_time: 3.349, memory: 6252, top1_acc: 0.1750, top5_acc: 0.6625, loss_cls: 2.3643, loss: 2.3643, grad_norm: 9.8010 2020-11-02 16:10:06,899 - mmaction - INFO - Epoch [1][30/92] lr: 1.000e-03, eta: 16:23:39, time: 7.578, data_time: 6.895, memory: 6252, top1_acc: 0.2125, top5_acc: 0.6625, loss_cls: 2.3160, loss: 2.3160, grad_norm: 10.1025

RuntimeError Traceback (most recent call last) in () ----> 1 gtf.Train();

6 frames /usr/local/lib/python3.6/dist-packages/torch/_utils.py in reraise(self) 383 # (https://bugs.python.org/issue2651), so we work around it. 384 msg = KeyErrorMessage(msg) --> 385 raise self.exc_type(msg)

RuntimeError: Caught RuntimeError in DataLoader worker process 2. Original Traceback (most recent call last): File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop data = fetcher.fetch(index) File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/_utils/fetch.py", line 44, in data = [self.dataset[idx] for idx in possibly_batched_index] File "/content/Monk_Object_Detection/18_mmaction/lib/mmaction/datasets/base.py", line 134, in getitem return self.prepare_train_frames(idx) File "/content/Monk_Object_Detection/18_mmaction/lib/mmaction/datasets/base.py", line 116, in prepare_train_frames return self.pipeline(results) File "/content/Monk_Object_Detection/18_mmaction/lib/mmaction/datasets/pipelines/compose.py", line 41, in call data = t(data) File "/content/Monk_Object_Detection/18_mmaction/lib/mmaction/datasets/pipelines/loading.py", line 698, in call container = decord.VideoReader(file_obj, num_threads=self.num_threads) File "/usr/local/lib/python3.6/dist-packages/decord/video_reader.py", line 47, in init raise RuntimeError("Error reading " + uri + "...") RuntimeError: Error reading 17727488 bytes...