MNIST For ML Beginners - https://www.tensorflow.org/get_started/mnist/beginners
Deep MNIST for Experts - https://www.tensorflow.org/get_started/mnist/pros
版本:
TensorFlow 1.2.0 + Flask 0.12 + Gunicorn 19.6
相关文章:
TensorFlow 之 入门体验
TensorFlow 之 手写数字识别MNIST
TensorFlow 之 物体检测
TensorFlow 之 构建人物识别系统
MNIST相当于机器学习界的Hello World。
这里在页面通过 Canvas 画一个数字,然后传给TensorFlow识别,分别给出Softmax回归模型、多层卷积网络的识别结果。
(1)文件结构
│ main.py
│ requirements.txt
│ runtime.txt
├─mnist
│ │ convolutional.py
│ │ model.py
│ │ regression.py
│ │ __init__.py
│ └─data
│ convolutional.ckpt.data-00000-of-00001
│ convolutional.ckpt.index
│ regression.ckpt.data-00000-of-00001
│ regression.ckpt.index
├─src
│ └─js
│ main.js
├─static
│ ├─css
│ │ bootstrap.min.css
│ └─js
│ jquery.min.js
│ main.js
└─templates
index.html
(2)训练数据
下载以下文件放入/tmp/data/,不用解压,训练代码会自动解压。
http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz
http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz
http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz
执行命令训练数据(Softmax回归模型、多层卷积网络)
- # python regression.py
- # python convolutional.py
执行完成后 在 mnist/data/ 里会生成以下几个文件,重新训练前需要把这几个文件先删掉。
convolutional.ckpt.index
regression.ckpt.data-00000-of-00001
regression.ckpt.index
(3)启动Web服务测试
- # cd /usr/local/tensorflow2/tensorflow-models/tf-mnist
- # pip install -r requirements.txt
- # gunicorn main:app --log-file=- --bind=localhost:8000
浏览器中访问:http://localhost:8000
*** 运行的TensorFlow版本、数据训练的模型、还有这里Canvas的转换都对识别率有一定的影响~!
(4)源代码
Web部分比较简单,页面上放置一个Canvas,鼠标抬起时将Canvas的图像通过Ajax传给后台API,然后显示API结果。
templates/index.html
main.py
- import numpy as np
- import tensorflow as tf
- from flask import Flask, jsonify, render_template, request
- from mnist import model
- x = tf.placeholder("float", [None, 784])
- sess = tf.Session()
- # restore trained data
- with tf.variable_scope("regression"):
- y1, variables = model.regression(x)
- saver = tf.train.Saver(variables)
- saver.restore(sess, "mnist/data/regression.ckpt")
- with tf.variable_scope("convolutional"):
- keep_prob = tf.placeholder("float")
- y2, variables = model.convolutional(x, keep_prob)
- saver = tf.train.Saver(variables)
- saver.restore(sess, "mnist/data/convolutional.ckpt")
- def regression(input):
- return sess.run(y1, feed_dict={x: input}).flatten().tolist()
- def convolutional(input):
- return sess.run(y2, feed_dict={x: input, keep_prob: 1.0}).flatten().tolist()
- # webapp
- app = Flask(__name__)
- @app.route('/api/mnist', methods=['POST'])
- def mnist():
- input = ((255 - np.array(request.json, dtype=np.uint8)) / 255.0).reshape(1, 784)
- output1 = regression(input)
- output2 = convolutional(input)
- print(output1)
- print(output2)
- return jsonify(results=[output1, output2])
- @app.route('/')
- def main():
- return render_template('index.html')
- if __name__ == '__main__':
- app.run()
mnist/model.py
- import tensorflow as tf
- # Softmax Regression Model
- def regression(x):
- W = tf.Variable(tf.zeros([784, 10]), name="W")
- b = tf.Variable(tf.zeros([10]), name="b")
- y = tf.nn.softmax(tf.matmul(x, W) + b)
- return y, [W, b]
- # Multilayer Convolutional Network
- def convolutional(x, keep_prob):
- def conv2d(x, W):
- return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
- def max_pool_2x2(x):
- return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
- def weight_variable(shape):
- initial = tf.truncated_normal(shape, stddev=0.1)
- return tf.Variable(initial)
- def bias_variable(shape):
- initial = tf.constant(0.1, shape=shape)
- return tf.Variable(initial)
- # First Convolutional Layer
- x_image = tf.reshape(x, [-1, 28, 28, 1])
- W_conv1 = weight_variable([5, 5, 1, 32])
- b_conv1 = bias_variable([32])
- h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
- h_pool1 = max_pool_2x2(h_conv1)
- # Second Convolutional Layer
- W_conv2 = weight_variable([5, 5, 32, 64])
- b_conv2 = bias_variable([64])
- h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
- h_pool2 = max_pool_2x2(h_conv2)
- # Densely Connected Layer
- W_fc1 = weight_variable([7 * 7 * 64, 1024])
- b_fc1 = bias_variable([1024])
- h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
- h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
- # Dropout
- h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
- # Readout Layer
- W_fc2 = weight_variable([1024, 10])
- b_fc2 = bias_variable([10])
- y = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
- return y, [W_conv1, b_conv1, W_conv2, b_conv2, W_fc1, b_fc1, W_fc2, b_fc2]
mnist/convolutional.py
- import os
- import model
- import tensorflow as tf
- from tensorflow.examples.tutorials.mnist import input_data
- data = input_data.read_data_sets("/tmp/data/", one_hot=True)
- # model
- with tf.variable_scope("convolutional"):
- x = tf.placeholder(tf.float32, [None, 784])
- keep_prob = tf.placeholder(tf.float32)
- y, variables = model.convolutional(x, keep_prob)
- # train
- y_ = tf.placeholder(tf.float32, [None, 10])
- cross_entropy = -tf.reduce_sum(y_ * tf.log(y))
- train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
- correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
- accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
- saver = tf.train.Saver(variables)
- with tf.Session() as sess:
- sess.run(tf.global_variables_initializer())
- for i in range(20000):
- batch = data.train.next_batch(50)
- if i % 100 == 0:
- train_accuracy = accuracy.eval(feed_dict={x: batch[0], y_: batch[1], keep_prob: 1.0})
- print("step %d, training accuracy %g" % (i, train_accuracy))
- sess.run(train_step, feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
- print(sess.run(accuracy, feed_dict={x: data.test.images, y_: data.test.labels, keep_prob: 1.0}))
- path = saver.save(
- sess, os.path.join(os.path.dirname(__file__), 'data', 'convolutional.ckpt'),
- write_meta_graph=False, write_state=False)
- print("Saved:", path)
mnist/regression.py
- import os
- import model
- import tensorflow as tf
- from tensorflow.examples.tutorials.mnist import input_data
- data = input_data.read_data_sets("/tmp/data/", one_hot=True)
- # model
- with tf.variable_scope("regression"):
- x = tf.placeholder(tf.float32, [None, 784])
- y, variables = model.regression(x)
- # train
- y_ = tf.placeholder("float", [None, 10])
- cross_entropy = -tf.reduce_sum(y_ * tf.log(y))
- train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
- correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
- accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
- saver = tf.train.Saver(variables)
- with tf.Session() as sess:
- sess.run(tf.global_variables_initializer())
- for _ in range(1000):
- batch_xs, batch_ys = data.train.next_batch(100)
- sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})
- print(sess.run(accuracy, feed_dict={x: data.test.images, y_: data.test.labels}))
- path = saver.save(
- sess, os.path.join(os.path.dirname(__file__), 'data', 'regression.ckpt'),
- write_meta_graph=False, write_state=False)
- print("Saved:", path)
参考:
http://memo.sugyan.com/entry/20151124/1448292129