search

dnth / yolov5-deepsparse-blogpost

By the end of this post, you will learn how to: Train a SOTA YOLOv5 model on your own data. Sparsify the model using SparseML quantization aware training, sparse transfer learning, and one-shot quantization. Export the sparsified model and run it using the DeepSparse engine at insane speeds. P/S: The end result - YOLOv5 on CPU at 180+ FPS using on
https://dicksonneoh.com/portfolio/supercharging_yolov5_180_fps_cpu/
53 stars 13 forks source link

unable resume training #6

Open chillum-codeX opened 2 years ago

chillum-codeX commented 2 years ago

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

chillum-codeX commented 2 years ago

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