search

vikrant7 / mobile-vod-bottleneck-lstm

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

training error #11

Open kaishijeng opened 4 years ago

kaishijeng commented 4 years ago

I use the following script to do training:

python3 train_mvod_basenet.py --datasets /home/sma/2TB/VID2015/ILSVRC/Data/VID --batch_size 60 --num_epochs 30 --width_mult 1

But got errors below:

2019-12-07 00:37:48,954 - root - INFO - Namespace(base_net_lr=None, batch_size=60, cache_path=None, checkpoint_folder='models/', datasets='/home/sma/2TB/VID2015/ILSVRC/Data/VID', 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) 2019-12-07 00:37:48,954 - root - INFO - Prepare training datasets. Traceback (most recent call last): File "train_mvod_basenet.py", line 206, in target_transform=target_transform) File "/home/sma/2TB/RCN/mobile-vod-bottleneck-lstm/datasets/vid_dataset_new.py", line 190, in init self.root = pathlib.Path(root) File "/home/sma/anaconda3/envs/directron2/lib/python3.6/pathlib.py", line 1001, in new self = cls._from_parts(args, init=False) File "/home/sma/anaconda3/envs/directron2/lib/python3.6/pathlib.py", line 656, in _from_parts drv, root, parts = self._parse_args(args) File "/home/sma/anaconda3/envs/directron2/lib/python3.6/pathlib.py", line 640, in _parse_args a = os.fspath(a) TypeError: expected str, bytes or os.PathLike object, not NoneType

Any idea why this happens? Thanks,

AmitYadu commented 4 years ago

i got the same error ?

stvogel commented 2 years ago

Just have a look at train_mvod_basenet.py. You also need to provide the path to a cache-directory when you run train_mvod_basenet.py with --cache_path /tmp