Microsoft azure自定义视觉服务的客户端
custom_vision_client的Python项目详细描述
py_custom_vision_客户端
这个存储库包含一个用于Custom Vision Service的简单python客户机。
使用量
# first, train a modelfromcustom_vision_clientimportTrainingClient,TrainingConfigazure_region="southcentralus"training_key="my-training-key"# from settings pane on customvision.aitraining_client=TrainingClient(TrainingConfig(azure_region,training_key))project_id=training_client.create_project("my-project-name").Idtraining_client.create_tag(project_id,"Cat")training_client.create_tag(project_id,"Dog")training_client.add_training_images(project_id,["kitten.jpg"],"Cat")training_client.add_training_images(project_id,["akita.png","spitz.png"],"Dog")training_client.add_training_images(project_id,["best-animal-pals.jpg"],"Cat","Dog")model_id=training_client.trigger_training(project_id).Id# then, use the model to predict:fromcustom_vision_clientimportPredictionClient,PredictionConfigazure_region="southcentralus"prediction_key="my-prediction-key"# from settings pane on customvision.aiprediction_client=PredictionClient(PredictionConfig(azure_region,project_id,prediction_key))predictions=prediction_client.classify_image("cat.jpg",model_id)# could also be a url to a filebest_prediction=max(predictions,key=lambda_:_.Probability)print(best_prediction.Tag)
命令行界面
您还可以通过命令行界面与自定义Vision服务进行交互：
# first, train a model python3 -m custom_vision_client.training \ --key="my-training-key"\ --projectname="my-project-name"\ --imagesroot="/path/to/images"# then, use the model to predict: python3 -m custom_vision_client.prediction \ --key="my-prediction-key"\ --projectid="my-project-id-from-training"\ --modelid="my-model-id-from-training"\ --image="path-or-url-to-image"
命令行界面假定您的训练图像是在文件夹中组织的 使每个文件夹都包含该标签的所有训练图像：
/path/to/images
├── label_one
│ ├── image_1.jpg
│ ├── image_2.png
│ └── image_3.png
└── label_two
├── image_4.jpg
└── image_5.jpg
欢迎加入QQ群-->： 979659372
