vikrant7 / mobile-vod-bottleneck-lstm

Implementation of Mobile Video Object Detection with Temporally-Aware Feature Maps using PyTorch
131 stars 37 forks source link

error in training #14

Closed AmitYadu closed 4 years ago

AmitYadu commented 4 years ago

python train_mvod_basenet.py --datasets /home/amit/ILSVRC2015_VID_initial/ILSVRC201 --batch_size 60 --num_epochs 30 --width_mult 1 2020-01-03 10:40:12,053 - root - INFO - Namespace(base_net_lr=None, batch_size=60, cache_path=None, checkpoint_folder='models/', datasets='/home/amit/ILSVRC2015_VID_initial/ILSVRC201', debug_steps=100, gamma=0.1, lr=0.003, milestones='80,100', momentum=0.9, num_epochs=30, num_workers=4, pretrained=None, resume=None, scheduler='multi-step', ssd_lr=None, t_max=120, use_cuda=True, validation_epochs=5, weight_decay=0.0005, width_mult=1.0) 2020-01-03 10:40:12,204 - root - INFO - Prepare training datasets. Traceback (most recent call last): File "train_mvod_basenet.py", line 207, in target_transform=target_transform) File "/home/amit/Downloads/mobile-vod-bottleneck-lstm-master/datasets/vid_dataset_new.py", line 190, in init self.root = pathlib.Path(root) File "/home/amit/anaconda3/lib/python3.7/pathlib.py", line 1010, in new self = cls._from_parts(args, init=False) File "/home/amit/anaconda3/lib/python3.7/pathlib.py", line 665, in _from_parts drv, root, parts = self._parse_args(args) File "/home/amit/anaconda3/lib/python3.7/pathlib.py", line 649, in _parse_args a = os.fspath(a) TypeError: expected str, bytes or os.PathLike object, not NoneType

please help