PaddleX/tutorials/train/image_classification/alexnet.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.cls import transforms
import paddlex as pdx

# 下载和解压蔬菜分类数据集
veg_dataset = 'https://bj.bcebos.com/paddlex/datasets/vegetables_cls.tar.gz'
pdx.utils.download_and_decompress(veg_dataset, path='./')

# 定义训练和验证时的transforms
# API说明https://paddlex.readthedocs.io/zh_CN/develop/apis/transforms/cls_transforms.html
train_transforms = transforms.Compose([
    transforms.RandomCrop(crop_size=224), transforms.RandomHorizontalFlip(),
    transforms.Normalize()
])
eval_transforms = transforms.Compose([
    transforms.ResizeByShort(short_size=256),
    transforms.CenterCrop(crop_size=224), 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-imagenet
train_dataset = pdx.datasets.ImageNet(
    data_dir='vegetables_cls',
    file_list='vegetables_cls/train_list.txt',
    label_list='vegetables_cls/labels.txt',
    transforms=train_transforms,
    shuffle=True)
eval_dataset = pdx.datasets.ImageNet(
    data_dir='vegetables_cls',
    file_list='vegetables_cls/val_list.txt',
    label_list='vegetables_cls/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
model = pdx.cls.AlexNet(num_classes=len(train_dataset.labels))
# AlexNet需要指定确定的input_shape
model.fixed_input_shape = [224, 224]

# API说明：https://paddlex.readthedocs.io/zh_CN/develop/apis/models/classification.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=10,
    train_dataset=train_dataset,
    train_batch_size=32,
    eval_dataset=eval_dataset,
    lr_decay_epochs=[4, 6, 8],
    learning_rate=0.0025,
    save_dir='output/alexnet',
    use_vdl=True)