yolov5-deepsparse-blogpost icon indicating copy to clipboard operation
yolov5-deepsparse-blogpost copied to clipboard

unable resume training

Open chillum-codeX opened this issue 2 years ago • 1 comments

unable to resume training when i pass the argument --resume it will add more epochs to my training

chillum-codeX avatar Jun 28 '22 03:06 chillum-codeX

python train.py --data pistols.yaml --cfg ./models_v5.0/yolov5s.yaml --weights zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/pruned_quant-aggressive_94?recipe_type=transfer --img 416 --batch-size 64 --hyp data/hyps/hyp.scratch.yaml --recipe ../recipes/yolov5.transfer_learn_pruned_quantized.md --optimizer SGD --device 0 --project yolov5-deepsparse --name yolov5s-sgd-pruned-quantized-transfer

this is the command i am using demo one when due to external factor training interrupt for ex power cut when i try to resume the training it will add more epochs to my training for ex. initial it was 220 epochs when i resume it was 440 epochs

i also used this one python train.py --resume

chillum-codeX avatar Jun 29 '22 09:06 chillum-codeX