HaloTrouvaille / YOLO-Multi-Backbones-Attention

Model Compression—YOLOv3 with multi lightweight backbones(ShuffleNetV2 HuaWei GhostNet), attention, prune and quantization
https://github.com/HaloTrouvaille/YOLO-Multi-Backbones-Attention
493 stars 118 forks source link

RuntimeError: Sizes of tensors must match except in dimension 2. Got 40 and 48 #6

Closed GUZ-lkc2018 closed 4 years ago

GUZ-lkc2018 commented 4 years ago

Thank you for your great work.An error occurred while I was running the code. python3 train.py --data data/oxfordhand.data --batch-size 1 --cfg cfg/yolov3-tiny-hand-se.cfg --epochs 100 -sr --s 0.001 --img-size 640 --weights '' ...... RuntimeError: Sizes of tensors must match except in dimension 2. Got 40 and 48 Can you give me some advice to solve this problem?

HaloTrouvaille commented 4 years ago

This version doesn‘t support attention mechanism. You can add my wechat ssswwwyyy111.