wangermeng2021 / Scaled-YOLOv4-tensorflow2

A Tensorflow2.x implementation of Scaled-YOLOv4 as described in Scaled-YOLOv4: Scaling Cross Stage Partial Network
Apache License 2.0
47 stars 18 forks source link

Cannot reproduce mAP with potholes data #20

Open tylertroy opened 2 years ago

tylertroy commented 2 years ago

I ran the command as specified in the docs to train on an RTX3090 using the potholes dataset as follows.

python train.py --use-pretrain True --model-type p5 --dataset-type voc --dataset dataset/pothole_voc --num-classes 1 --class-names pothole.names --voc-train-set dataset_1,train --voc-val-set dataset_1,val  --epochs 200 --batch-size 4 --multi-scale 320,352,384,416,448,480,512 --augment ssd_random_crop

However I cannot reproduce the mAP as presented. image

Similarly the training loss looks quite different. image

Any thoughts on what I might be doing wrong? Or perhaps there has been a material change to the repo since those results were posted.

Feedback appreciated and thanks for providing this good work to the community.