PaddleX/tutorials/train/object_detection/yolov3_mobilenetv1.py

# 环境变量配置，用于控制是否使用GPU
# 说明文档：https://paddlex.readthedocs.io/zh_CN/develop/appendix/parameters.html#gpu
import os
os.environ['CUDA_VISIBLE_DEVICES'] = '0'

from paddlex.det import transforms
import paddlex as pdx

# 下载和解压昆虫检测数据集
insect_dataset = 'https://bj.bcebos.com/paddlex/datasets/insect_det.tar.gz'
pdx.utils.download_and_decompress(insect_dataset, path='./')

# 定义训练和验证时的transforms
# API说明 https://paddlex.readthedocs.io/zh_CN/develop/apis/transforms/det_transforms.html
train_transforms = transforms.Compose([
    transforms.MixupImage(mixup_epoch=250),
    transforms.RandomDistort(),
    transforms.RandomExpand(),
    transforms.RandomCrop(),
    transforms.Resize(
        target_size=608, interp='RANDOM'),
    transforms.RandomHorizontalFlip(),
    transforms.Normalize(),
])

eval_transforms = transforms.Compose([
    transforms.Resize(
        target_size=608, interp='CUBIC'),
    transforms.Normalize(),
])

# 定义训练和验证所用的数据集
# API说明：https://paddlex.readthedocs.io/zh_CN/develop/apis/datasets.html#paddlex-datasets-vocdetection
train_dataset = pdx.datasets.VOCDetection(
    data_dir='insect_det',
    file_list='insect_det/train_list.txt',
    label_list='insect_det/labels.txt',
    transforms=train_transforms,
    shuffle=True)
eval_dataset = pdx.datasets.VOCDetection(
    data_dir='insect_det',
    file_list='insect_det/val_list.txt',
    label_list='insect_det/labels.txt',
    transforms=eval_transforms)

# 初始化模型，并进行训练
# 可使用VisualDL查看训练指标，参考https://paddlex.readthedocs.io/zh_CN/develop/train/visualdl.html
num_classes = len(train_dataset.labels)

# API说明: https://paddlex.readthedocs.io/zh_CN/develop/apis/models/detection.html#paddlex-det-yolov3
model = pdx.det.YOLOv3(num_classes=num_classes, backbone='MobileNetV1')

# API说明: https://paddlex.readthedocs.io/zh_CN/develop/apis/models/detection.html#train
# 各参数介绍与调整说明：https://paddlex.readthedocs.io/zh_CN/develop/appendix/parameters.html
model.train(
    num_epochs=270,
    train_dataset=train_dataset,
    train_batch_size=8,
    eval_dataset=eval_dataset,
    learning_rate=0.000125,
    lr_decay_epochs=[210, 240],
    save_dir='output/yolov3_mobilenetv1',
    use_vdl=True)