SpursLipu / YOLOv3v4-ModelCompression-MultidatasetTraining-Multibackbone

YOLO ModelCompression MultidatasetTraining
GNU General Public License v3.0
444 stars 136 forks source link

quantizaion problem #82

Open saeedkhanehgir opened 3 years ago

saeedkhanehgir commented 3 years ago

Hi thanks for this project I use command below for training with quantization but get problem.

python train.py -pt --data cfg/obj.data --batch-size 4 --weights weights/yolov3-tiny.weights --cfg cfg/yolov3-tiny.cfg -sr --s .001 --prune 0 --quantized 2

error: File "train.py", line 920, in WarmupForQ(hyp, step=i, a_bit=a_bit, w_bit=w_bit) File "train.py", line 799, in WarmupForQ bn_weights = gather_bn_weights(model.module_list, [idx]) NameError: name 'idx' is not defined