memory - Tensorflow、Flask 和 TFLearn 内存泄漏

Question

我正在运行以下程序，每次点击“构建”API 调用时，我都会看到进程完成后又占用了 1 GB 内存。我试图从内存中消除一切，但我不确定还剩下什么。

import tensorflow as tf
import tflearn
from flask import Flask, jsonify
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.conv import conv_2d, max_pool_2d
from tflearn.layers.normalization import local_response_normalization
from tflearn.layers.estimator import regression

app = Flask(__name__)

keep_prob = .8
num_labels = 3
batch_size = 64

class AlexNet():

    def __init__(self):

        @app.route('/build')
        def build():
            g = tf.Graph()
            with g.as_default():
                sess = tf.Session()

                # Building 'AlexNet'
                network = input_data(shape=[None, 227, 227, 3])
                network = conv_2d(network, 96, 11, strides=4, activation='relu')
                network = max_pool_2d(network, 3, strides=2)
                network = local_response_normalization(network)
                network = conv_2d(network, 256, 5, activation='relu')
                network = max_pool_2d(network, 3, strides=2)
                network = local_response_normalization(network)
                network = conv_2d(network, 384, 3, activation='relu')
                network = conv_2d(network, 384, 3, activation='relu')
                network = conv_2d(network, 256, 3, activation='relu')
                network = max_pool_2d(network, 3, strides=2)
                network = local_response_normalization(network)
                network = fully_connected(network, 4096, activation='tanh')
                network = dropout(network, keep_prob)
                network = fully_connected(network, 4096, activation='tanh')
                network = dropout(network, keep_prob)
                network = fully_connected(network, num_labels, activation='softmax')
                network = regression(network, optimizer="adam",
                                     loss='categorical_crossentropy',
                                     learning_rate=0.001, batch_size=batch_size)

                model = tflearn.DNN(network, tensorboard_dir="./tflearn_logs/",
                                    checkpoint_path=None, tensorboard_verbose=0, session=sess)

                sess.run(tf.initialize_all_variables())
                sess.close()

            tf.reset_default_graph()

            del g
            del sess
            del model
            del network
            return jsonify(status=200)


if __name__ == "__main__":
    AlexNet()
    app.run(host='0.0.0.0', port=5000, threaded=True)

Answer 1

我不确定您是否找到了答案，但恕我直言，您不应该将长时间运行的任务放入 HTTP 请求处理程序中。因为 HTTP 是无状态的并且应该几乎立即响应调用。这就是为什么我们有任务队列、异步任务等概念。服务器端开发的经验法则是尽快响应请求。如果你尝试在 HTTP 请求中构建一个卷积深度神经网络，那么它并不真正可行也是很正常的。因为理想的 HTTP 请求应该在几秒钟内响应。您的 DNN 分类器 session 运行可能需要太多秒(需要尝试)。

最黑客的解决方案是在请求中创建一个 python 线程，并让请求响应 HTTP 调用而不阻塞。同时，您的线程可以继续构建您的模型。然后您可以在某处编写您的模型或发送邮件通知等。

给你:

How can I add a background thread to flask?