Deploy a trained model

简介: 本次教程的目的是带领大家学会用 Tensorflow serving 部署训练好的模型这里我们用到的数据集是 Fashion MNIST,所以训练出来的模型可以实现以下几个类别的分类

本次教程的目的是带领大家学会用 Tensorflow serving 部署训练好的模型

这里我们用到的数据集是 Fashion MNIST,所以训练出来的模型可以实现以下几个类别的分类

'T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',
               'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot'

因为这篇教程主要关注部署,所以我们直接从已经训练好的模型开始,保存的格式是 SavedModel,如上图所示

在这之前呢,我们需要先安装好 tensorflow_model_server

接下来我们可以在控制台执行以下指令,就可以启动一个 serving 服务了,我们可以通过 REST API 进行请求,并返回预测结果

import requests
headers = {"content-type": "application/json"}
json_response = requests.post('http://localhost:8501/v1/models/fashion_mnist:predict', data=data, headers=headers)

predictions = json.loads(json_response.text)["predictions"]

show(0, "The model thought this was a {} (class {}), and it was actually a {} (class {})".format(class_names[np.argmax(predictions[0])], np.argmax(predictions[0]), class_names[test_labels[0]], test_labels[0]))

上图是通过请求,然后预测得到的结果,到此,我们实现了模型的 Tensorflow serving 的部署

代码链接: https://codechina.csdn.net/csdn_codechina/enterprise_technology/-/blob/master/tensorflow_serving.ipynb

目录
相关文章
|
4月前
|
JavaScript
v-model和:model的区别
v-model和:model的区别
36 0
|
jenkins Unix Shell
Jenkins 利用Build With Parameters Plugin实现Jenkins参数化构建
Jenkins 利用Build With Parameters Plugin实现Jenkins参数化构建
388 0
|
数据格式
ValueError: This model has not yet been built. Build the model first by calling `build()` or calling
ValueError: This model has not yet been built. Build the model first by calling `build()` or calling
157 0
ValueError: This model has not yet been built. Build the model first by calling `build()` or calling
【解决方案】The opset version of the onnx model is 12, only model with opset_version 10/11 is supported.
【解决方案】The opset version of the onnx model is 12, only model with opset_version 10/11 is supported.
475 0
|
存储 算法 Python
【mflow系列6】mlflow model registry
【mflow系列6】mlflow model registry
248 0
【mflow系列6】mlflow model registry
【yolov5报错】Can‘t get attribute ‘SPPF‘ on <module ‘models.common‘ from ‘--yolov5-5.0\models\common.py
【yolov5报错】Can‘t get attribute ‘SPPF‘ on <module ‘models.common‘ from ‘--yolov5-5.0\models\common.py
999 0
An example of EXPORT / IMPORT usage - in office integration and odata metadata model cache
An example of EXPORT / IMPORT usage - in office integration and odata metadata model cache
An example of EXPORT / IMPORT usage - in office integration and odata metadata model cache
|
API
Product Master data model harmonization guiding principle
Product Master data model harmonization guiding principle
126 0
Product Master data model harmonization guiding principle