文档指导：
第一步：重新安装环境
1.启动Notebook并打开
2.重新执行安装的三条命令
第二步：指针和刻度分割模型训练
1.调用paddlex
import paddlex as pdxfrom paddlex import transforms as T
2.定义训练和验证时的transforms
**详细API说明参考：**https://github.com/PaddlePaddle/PaddleX/blob/release/2.0-rc/paddlex/cv/transforms/operators.py
train_transforms = T.Compose([ T.Resize(target_size=512), T.RandomHorizontalFlip(), T.Normalize( mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]),]) eval_transforms = T.Compose([ T.Resize(target_size=512), T.Normalize( mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]),])
3.下载和解压指针刻度分割数据集
meter_seg_dataset = 'https://bj.bcebos.com/paddlex/examples/meter_reader/datasets/meter_seg.tar.gz'pdx.utils.download_and_decompress(meter_seg_dataset, path='./')
4.定义训练和验证所用的数据集，配置相应路径
**详细API说明参考：**https://github.com/PaddlePaddle/PaddleX/blob/release/2.0-rc/paddlex/cv/datasets/seg_dataset.py#L22
train_dataset = pdx.datasets.SegDataset( data_dir='meter_seg', file_list='meter_seg/train.txt', label_list='meter_seg/labels.txt', transforms=train_transforms, shuffle=True) eval_dataset = pdx.datasets.SegDataset( data_dir='meter_seg', file_list='meter_seg/val.txt', label_list='meter_seg/labels.txt', transforms=eval_transforms, shuffle=False)
5.选择PaddleX内置的DeepLabV3P模型进行训练
**API说明：**https://github.com/PaddlePaddle/PaddleX/blob/release/2.0-rc/paddlex/cv/models/segmenter.py#L150
num_classes = len(train_dataset.labels)model = pdx.seg.DeepLabV3P( num_classes=num_classes, backbone='ResNet50_vd', use_mixed_loss=True)
6.设置训练时的参数
各参数介绍与调整说明：https://paddlex.readthedocs.io/zh_CN/develop/appendix/parameters.html
model.train( num_epochs=2, train_dataset=train_dataset, train_batch_size=4, eval_dataset=eval_dataset, pretrain_weights='IMAGENET', learning_rate=0.1, save_dir='output/deeplabv3p_r50vd')
7.训练结束后查看bestmodel
第三步：保存Notebook并关闭、停止运行
提示：Notebook一旦运行即会开始计费，如果不用请及时停止！以免浪费免费额度
截图示例：
