I don't know, how to resume from checkpoint data.

[sounansu]

I try to resume from checkpoint data, as blow.

python train_mvod_basenet.py --datasets ./ILSVRC --cache_path ./ --batch_size 60 --num_epochs 30 --width_mult 1 --resume models/basenet/WM-1.0-Epoch-15-Loss-111.27649793882628.pth

But, I can not restart training from epoch 15

2020-03-26 14:53:06,380 - root - INFO - Prepare training datasets.
2020-03-26 14:53:06,610 - root - INFO - using default Imagenet VID classes.
2020-03-26 14:53:22,396 - root - INFO - gt roidb loaded from ./train_VID_gt_db.pkl
2020-03-26 14:53:22,396 - root - INFO - Stored labels into file models/vid-model-labels.txt.
2020-03-26 14:53:22,396 - root - INFO - Train dataset size: 1086132
2020-03-26 14:53:22,396 - root - INFO - Prepare Validation datasets.
2020-03-26 14:53:22,398 - root - INFO - using default Imagenet VID classes.
2020-03-26 14:53:22,527 - root - INFO - gt roidb loaded from ./val_VID_gt_db.pkl
2020-03-26 14:53:22,527 - root - INFO - <datasets.vid_dataset_new.ImagenetDataset object at 0x7fe89f1a8be0>
2020-03-26 14:53:22,527 - root - INFO - validation dataset size: 11080
2020-03-26 14:53:22,527 - root - INFO - Build network.
2020-03-26 14:53:22,540 - root - INFO - Initializing weights of base net
2020-03-26 14:53:22,563 - root - INFO - Initializing weights of SSD
Updating weights from resume model
2020-03-26 14:53:23,626 - root - INFO - Learning rate: 0.003, Base net learning rate: 0.003, Extra Layers learning rate: 0.003.
2020-03-26 14:53:23,626 - root - INFO - Start training from epoch 0.

Please teach me how to resume from checkpoint data!

Thank you!