Closed StawEndl closed 1 year ago
Hi, you can directly set the MODEL.WEIGHTS as model_0159999.pth
to use it as the pretrained checkpoint.
python train_net.py --dist-url 'tcp://127.0.0.1:50163' \
--num-gpus 8 \
--config-file <path-to-config> \
MODEL.WEIGHTS model_0159999.pth \
OUTPUT_DIR <output_dir> WANDB.NAME <name>
hi, i want to use pretained model for new trainning, how should i do? i want to trainning with dataset B, and i want to use model_0159999.pth which is producted at trainning on dataset A, as the pretrained model.