Pretrained Model not Loading

[eriche7133]

When I run the following line:

CUDA_VISIBLE_DEVICES=0,1,2,3 python train.py --backbone resnet --lr 0.007 --workers 4 --epochs 50 --batch-size 16 --gpu-ids 0,1,2,3 --checkname deeplab-resnet --eval-interval 1 --dataset pascal --resume 'deeplab-resnet.pth.tar'

based off of train_voc.sh, I get the following error:

Traceback (most recent call last): File "train.py", line 303, in main() File "train.py", line 292, in main trainer = Trainer(args) File "train.py", line 84, in init self.optimizer.load_state_dict(checkpoint['optimizer']) File "/home/eriche/anaconda3/envs/deeplabEnv/lib/python3.7/site-packages/torch/optim/optimizer.py", line 114, in load_state_dict raise ValueError("loaded state dict contains a parameter group " ValueError: loaded state dict contains a parameter group that doesn't match the size of optimizer's group

This is using the Resnet pretrained model downloaded from the GoogleDrive link on the README. Any help would be greatly appreciated.

[seeyouagain111]

i have the same question,have you fix it?

[kangmengmeng]

I have meet the same question,too.

[johsnows]

I have meet the same question,too.

[learningyan]

the same question.....

[xc769458796]

me too，do you resolve it?

[xc769458796]

i solved it,you should set --freeze-bn True

[CoolLoveBoy]

i solved it,you should set --freeze-bn True

I have set --freeze-bn True, but it has the same error