github:Zylo
使用的torch和torchvision版本,torch和torchvision的版本要对应,cuda版本一致
![](https://img.laitimes.com/img/9ZDMuAjOiMmIsIjOiQnIsIyZuBnL4QTO1QTMwATM5ETNwEjMwIzLc52YucWbp5GZzNmLn9Gbi1yZtl2Lc9CX6MHc0RHaiojIsJye.png)
数据集
将数据集做成coco格式
# for example, coco2017
datasets/
-coco2017/
-train2017/
-000000000001.jpg
-000000000002.jpg
-000000000003.jpg
-val2017/
-000000000004.jpg
-000000000005.jpg
-000000000006.jpg
-annotations
-instances_train2017.json
-instances_val2017.json
其中,annotations中的类别需要从1开始,不从0开始
修改project文件下的yml文件
project_name: logo # also the folder name of the dataset that under data_path folder
train_set: train
val_set: val
num_gpus: 1
obj_list: [ 'adidas0', 'chanel','gucci','hh','lacoste','mk','nike','prada','puma','supreme' ]
训练
- from scratch
python train.py -c 0 --batch_size 64 --optim sgd --lr 8e-2
- Train a custom dataset with pretrained weights
python train.py -c 2 -p your_project_name --batch_size 8 --lr 1e-3 --num_epochs 10 --load_weights /path/to/your/weights/efficientdet-d2.pth --head_only True
评估
python coco_eval.py -p your_project_name -c 5 -w /path/to/your/weights
inference
python efficientdet_test.py