caffe\tesorflow提供服务

最新推荐文章于 2024-09-20 10:00:14 发布

zbxzc

最新推荐文章于 2024-09-20 10:00:14 发布

阅读量859

点赞数

文章标签：深度学习

本文链接：https://blog.csdn.net/u014568921/article/details/77689591

版权

调研专栏收录该内容

0 篇文章 0 订阅

订阅专栏

caffe提供服务

Flask文件上传（一）：原生实现

Caffe+flask CNN算法服务器搭建

Caffe，PyCaffe上手实践2 基于Flask的图像分类服务

https://github.com/kendricktan/xraychecker

https://github.com/zzningxp/flask-image-retrieval

https://github.com/sugyan/inception-app-example

Tensorflow Serving with support for Caffe

https://github.com/rayglover-ibm/serving-caffe

tensorflow提供服务

https://www.tensorflow.org/serving/

https://github.com/tensorflow/serving/tree/master/tensorflow_serving/example

https://github.com/llSourcell/How-to-Deploy-a-Tensorflow-Model-in-Production

Bazel 安装及遇到的问题

https://github.com/bazelbuild/bazel/releases

https://stackoverflow.com/questions/42519010/how-to-do-batching-in-tensorflow-serving

安装tensorflow serving总结

TF_Serving 部署一个模型

TensorFlow Serving 尝尝鲜

tensorflow serving

Tensorflow serving(tf_serving) 安装测试说明

Tensorflow serving的编译

Tensorflow Serving初体验

Centos7部署Tensorflow Serving

tensorflow serving for centos 7.2

tensorflow-serving源码理解

flask快速搭建tensorflow http服务

Tensorflow Serving 模型部署和服务

http://www.cnblogs.com/YouXiangLiThon/tag/tensorflow%20serving/

模型导出

tf.train.Saver
用于保存和恢复Variable。它可以非常方便的保存当前模型的变量或者倒入之前训练好的变量。一个最简单的运用：
saver - tf.train.Saver()

Save the variables to disk.
saver.save(sess, “/tmp/test.ckpt”)

Restore variables from disk.
saver.restore(sess, “/tmp/test.ckpt”)

tf.contrib.session_bundle.exporter.Exporter
导出模型还需要这个 Exporter 的协助。
Exporter 的基本使用方式是
1.传入 saver 构造一个实例
2.调用 init 定义模型的 graph 和 input/output
3.使用 export 导出为文件

import numpy as np
import tensorflow as tf
from tensorflow.contrib.session_bundle import exporter
model_path = 'snapshots'  # 'experiments/train_experiment/checkpoints'
# Tensorflow specific configuration
config = tf.ConfigProto(allow_soft_placement=True)
config.gpu_options.allow_growth = True
sess = tf.Session(config=config)
latest_checkpoint = tf.train.latest_checkpoint(model_path)
if latest_checkpoint:
        print("Loading model checkpoint {} ...\n".format(latest_checkpoint))
        metagraph_file = latest_checkpoint + '.meta'
        saver = tf.train.import_meta_graph(metagraph_file)
        saver.restore(sess, latest_checkpoint)
        print("Checkpoint loaded\n\n")
else:
        print("No checkpoints available!\n\n")
image_data = sess.graph.get_tensor_by_name('input/Placeholder:0')
softmax_tensor     = sess.graph.get_tensor_by_name('output/Softmax:0')
model_exporter = exporter.Exporter(saver)
model_exporter.init(sess.graph.as_graph_def(),
                        named_graph_signatures={
                        'inputs': exporter.generic_signature({'x': image_data}),
                        'outputs': exporter.generic_signature({'y': softmax_tensor})}
    )
model_exporter.export('model', tf.constant(1), sess)

https://github.com/triagemd/model-serving

https://github.com/songbinliu/inceptionServer

https://github.com/vishh/tf-serving-base

https://github.com/tanveer941/Object-detection-sever

https://github.com/peppaseven/object_detector_server

https://github.com/arixlin/server_object_detection

https://github.com/BlueLens/bl-detect

https://github.com/jsonw99/object_detect_serving

https://github.com/movchan74/tensorflow_serving_examples

https://github.com/TensorLab/tensorfx

https://github.com/aaxwaz/Serving-TensorFlow-Model

https://github.com/hetaoaoao/tensorflow_web_deploy