0
雷鋒網按：本文作者Coldwings，本文整理自作者在知乎發布的文章《利用微信監管你的TF訓練》，雷鋒網獲其授權發布。
之前回答問題【在機器學習模型的訓練期間，大概幾十分鐘到幾小時不等，大家都會在等實驗的時候做什么？】的時候，說到可以用微信來管著訓練，完全不用守著。沒想到這么受歡迎……
不知道有哪些朋友是在TF/keras/chainer/mxnet等框架下用python擼的….…
這可是python啊……上itchat，弄個微信號加自己為好友（或者自己發自己），訓練進展跟著一路發消息給自己就好了，做了可視化的話順便把圖也一并發過來。
然后就能安心睡覺/逛街/泡妞/寫答案了。
講道理，甚至簡單的參數調整都可以照著用手機來……
大體效果如下
當然可以做得更全面一些。最可靠的辦法自然是干脆地做一個http服務或者一個rpc，然而這樣往往太麻煩。本著簡單高效的原則，幾行代碼能起到效果方便自己當然是最好的，接入微信或者web真就是不錯的選擇了。只是查看的話，TensorBoard就很好，但是如果想加入一些自定義操作，還是自行定制的。echat.js做成web，或者itchat做個微信服務，都是挺不賴的選擇。
這里折騰一個例子。以TensorFlow的example中，利用CNN處理MNIST的程序為例，我們做一點點小小的修改。
首先這里放上寫完的代碼：
#!/usr/bin/env python
# coding: utf-8
'''
A Convolutional Network implementation example using TensorFlow library.
This example is using the MNIST database of handwritten digits
(http://yann.lecun.com/exdb/mnist/)
Author: Aymeric Damien
Project: https://github.com/aymericdamien/TensorFlow-Examples/
Add a itchat controller with multi thread
'''
from __future__ import print_function
import tensorflow as tf
# Import MNIST data
from tensorflow.examples.tutorials.mnist import input_data
# Import itchat & threading
import itchat
import threading
# Create a running status flag
lock = threading.Lock()
running = False
# Parameters
learning_rate = 0.001
training_iters = 200000
batch_size = 128
display_step = 10
def nn_train(wechat_name, param):
global lock, running
# Lock
with lock:
running = True
# mnist data reading
mnist = input_data.read_data_sets("data/", one_hot=True)
# Parameters
# learning_rate = 0.001
# training_iters = 200000
# batch_size = 128
# display_step = 10
learning_rate, training_iters, batch_size, display_step = param
# Network Parameters
n_input = 784 # MNIST data input (img shape: 28*28)
n_classes = 10 # MNIST total classes (0-9 digits)
dropout = 0.75 # Dropout, probability to keep units
# tf Graph input
x = tf.placeholder(tf.float32, [None, n_input])
y = tf.placeholder(tf.float32, [None, n_classes])
keep_prob = tf.placeholder(tf.float32) #dropout (keep probability)
# Create some wrappers for simplicity
def conv2d(x, W, b, strides=1):
# Conv2D wrapper, with bias and relu activation
x = tf.nn.conv2d(x, W, strides=[1, strides, strides, 1], padding='SAME')
x = tf.nn.bias_add(x, b)
return tf.nn.relu(x)
def maxpool2d(x, k=2):
# MaxPool2D wrapper
return tf.nn.max_pool(x, ksize=[1, k, k, 1], strides=[1, k, k, 1],
padding='SAME')
# Create model
def conv_net(x, weights, biases, dropout):
# Reshape input picture
x = tf.reshape(x, shape=[-1, 28, 28, 1])
# Convolution Layer
conv1 = conv2d(x, weights['wc1'], biases['bc1'])
# Max Pooling (down-sampling)
conv1 = maxpool2d(conv1, k=2)
# Convolution Layer
conv2 = conv2d(conv1, weights['wc2'], biases['bc2'])
# Max Pooling (down-sampling)
conv2 = maxpool2d(conv2, k=2)
# Fully connected layer
# Reshape conv2 output to fit fully connected layer input
fc1 = tf.reshape(conv2, [-1, weights['wd1'].get_shape().as_list()[0]])
fc1 = tf.add(tf.matmul(fc1, weights['wd1']), biases['bd1'])
fc1 = tf.nn.relu(fc1)
# Apply Dropout
fc1 = tf.nn.dropout(fc1, dropout)
# Output, class prediction
out = tf.add(tf.matmul(fc1, weights['out']), biases['out'])
return out
# Store layers weight & bias
weights = {
# 5x5 conv, 1 input, 32 outputs
'wc1': tf.Variable(tf.random_normal([5, 5, 1, 32])),
# 5x5 conv, 32 inputs, 64 outputs
'wc2': tf.Variable(tf.random_normal([5, 5, 32, 64])),
# fully connected, 7*7*64 inputs, 1024 outputs
'wd1': tf.Variable(tf.random_normal([7*7*64, 1024])),
# 1024 inputs, 10 outputs (class prediction)
'out': tf.Variable(tf.random_normal([1024, n_classes]))
}
biases = {
'bc1': tf.Variable(tf.random_normal([32])),
'bc2': tf.Variable(tf.random_normal([64])),
'bd1': tf.Variable(tf.random_normal([1024])),
'out': tf.Variable(tf.random_normal([n_classes]))
}
# Construct model
pred = conv_net(x, weights, biases, keep_prob)
# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
# Evaluate model
correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
# Initializing the variables
init = tf.global_variables_initializer()
# Launch the graph
with tf.Session() as sess:
sess.run(init)
step = 1
# Keep training until reach max iterations
print('Wait for lock')
with lock:
run_state = running
print('Start')
while step * batch_size < training_iters and run_state:
batch_x, batch_y = mnist.train.next_batch(batch_size)
# Run optimization op (backprop)
sess.run(optimizer, feed_dict={x: batch_x, y: batch_y,
keep_prob: dropout})
if step % display_step == 0:
# Calculate batch loss and accuracy
loss, acc = sess.run([cost, accuracy], feed_dict={x: batch_x,
y: batch_y,
keep_prob: 1.})
print("Iter " + str(step*batch_size) + ", Minibatch Loss= " + \
"{:.6f}".format(loss) + ", Training Accuracy= " + \
"{:.5f}".format(acc))
itchat.send("Iter " + str(step*batch_size) + ", Minibatch Loss= " + \
"{:.6f}".format(loss) + ", Training Accuracy= " + \
"{:.5f}".format(acc), wechat_name)
step += 1
with lock:
run_state = running
print("Optimization Finished!")
itchat.send("Optimization Finished!", wechat_name)
# Calculate accuracy for 256 mnist test images
print("Testing Accuracy:", \
sess.run(accuracy, feed_dict={x: mnist.test.images[:256],
y: mnist.test.labels[:256],
keep_prob: 1.}))
itchat.send("Testing Accuracy: %s" %
sess.run(accuracy, feed_dict={x: mnist.test.images[:256],
y: mnist.test.labels[:256],
keep_prob: 1.}), wechat_name)
with lock:
running = False
@itchat.msg_register([itchat.content.TEXT])
def chat_trigger(msg):
global lock, running, learning_rate, training_iters, batch_size, display_step
if msg['Text'] == u'開始':
print('Starting')
with lock:
run_state = running
if not run_state:
try:
threading.Thread(target=nn_train, args=(msg['FromUserName'], (learning_rate, training_iters, batch_size, display_step))).start()
except:
msg.reply('Running')
elif msg['Text'] == u'停止':
print('Stopping')
with lock:
running = False
elif msg['Text'] == u'參數':
itchat.send('lr=%f, ti=%d, bs=%d, ds=%d'%(learning_rate, training_iters, batch_size, display_step),msg['FromUserName'])
else:
try:
param = msg['Text'].split()
key, value = param
print(key, value)
if key == 'lr':
learning_rate = float(value)
elif key == 'ti':
training_iters = int(value)
elif key == 'bs':
batch_size = int(value)
elif key == 'ds':
display_step = int(value)
except:
pass
if __name__ == '__main__':
itchat.auto_login(hotReload=True)
itchat.run()
這段代碼里面，我所做的修改主要是：
0.導入了itchat和threading
1. 把原本的腳本里網絡構成和訓練的部分甩到了一個函數nn_train里
def nn_train(wechat_name, param):
global lock, running
# Lock
with lock:
running = True
# mnist data reading
mnist = input_data.read_data_sets("data/", one_hot=True)
# Parameters
# learning_rate = 0.001
# training_iters = 200000
# batch_size = 128
# display_step = 10
learning_rate, training_iters, batch_size, display_step = param
# Network Parameters
n_input = 784 # MNIST data input (img shape: 28*28)
n_classes = 10 # MNIST total classes (0-9 digits)
dropout = 0.75 # Dropout, probability to keep units
# tf Graph input
x = tf.placeholder(tf.float32, [None, n_input])
y = tf.placeholder(tf.float32, [None, n_classes])
keep_prob = tf.placeholder(tf.float32) #dropout (keep probability)
# Create some wrappers for simplicity
def conv2d(x, W, b, strides=1):
# Conv2D wrapper, with bias and relu activation
x = tf.nn.conv2d(x, W, strides=[1, strides, strides, 1], padding='SAME')
x = tf.nn.bias_add(x, b)
return tf.nn.relu(x)
def maxpool2d(x, k=2):
# MaxPool2D wrapper
return tf.nn.max_pool(x, ksize=[1, k, k, 1], strides=[1, k, k, 1],
padding='SAME')
# Create model
def conv_net(x, weights, biases, dropout):
# Reshape input picture
x = tf.reshape(x, shape=[-1, 28, 28, 1])
# Convolution Layer
conv1 = conv2d(x, weights['wc1'], biases['bc1'])
# Max Pooling (down-sampling)
conv1 = maxpool2d(conv1, k=2)
# Convolution Layer
conv2 = conv2d(conv1, weights['wc2'], biases['bc2'])
# Max Pooling (down-sampling)
conv2 = maxpool2d(conv2, k=2)
# Fully connected layer
# Reshape conv2 output to fit fully connected layer input
fc1 = tf.reshape(conv2, [-1, weights['wd1'].get_shape().as_list()[0]])
fc1 = tf.add(tf.matmul(fc1, weights['wd1']), biases['bd1'])
fc1 = tf.nn.relu(fc1)
# Apply Dropout
fc1 = tf.nn.dropout(fc1, dropout)
# Output, class prediction
out = tf.add(tf.matmul(fc1, weights['out']), biases['out'])
return out
# Store layers weight & bias
weights = {
# 5x5 conv, 1 input, 32 outputs
'wc1': tf.Variable(tf.random_normal([5, 5, 1, 32])),
# 5x5 conv, 32 inputs, 64 outputs
'wc2': tf.Variable(tf.random_normal([5, 5, 32, 64])),
# fully connected, 7*7*64 inputs, 1024 outputs
'wd1': tf.Variable(tf.random_normal([7*7*64, 1024])),
# 1024 inputs, 10 outputs (class prediction)
'out': tf.Variable(tf.random_normal([1024, n_classes]))
}
biases = {
'bc1': tf.Variable(tf.random_normal([32])),
'bc2': tf.Variable(tf.random_normal([64])),
'bd1': tf.Variable(tf.random_normal([1024])),
'out': tf.Variable(tf.random_normal([n_classes]))
}
# Construct model
pred = conv_net(x, weights, biases, keep_prob)
# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
# Evaluate model
correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
# Initializing the variables
init = tf.global_variables_initializer()
# Launch the graph
with tf.Session() as sess:
sess.run(init)
step = 1
# Keep training until reach max iterations
print('Wait for lock')
with lock:
run_state = running
print('Start')
while step * batch_size < training_iters and run_state:
batch_x, batch_y = mnist.train.next_batch(batch_size)
# Run optimization op (backprop)
sess.run(optimizer, feed_dict={x: batch_x, y: batch_y,
keep_prob: dropout})
if step % display_step == 0:
# Calculate batch loss and accuracy
loss, acc = sess.run([cost, accuracy], feed_dict={x: batch_x,
y: batch_y,
keep_prob: 1.})
print("Iter " + str(step*batch_size) + ", Minibatch Loss= " + \
"{:.6f}".format(loss) + ", Training Accuracy= " + \
"{:.5f}".format(acc))
itchat.send("Iter " + str(step*batch_size) + ", Minibatch Loss= " + \
"{:.6f}".format(loss) + ", Training Accuracy= " + \
"{:.5f}".format(acc), wechat_name)
step += 1
with lock:
run_state = running
print("Optimization Finished!")
itchat.send("Optimization Finished!", wechat_name)
# Calculate accuracy for 256 mnist test images
print("Testing Accuracy:", \
sess.run(accuracy, feed_dict={x: mnist.test.images[:256],
y: mnist.test.labels[:256],
keep_prob: 1.}))
itchat.send("Testing Accuracy: %s" %
sess.run(accuracy, feed_dict={x: mnist.test.images[:256],
y: mnist.test.labels[:256],
keep_prob: 1.}), wechat_name)
with lock:
running = False
這里大部分是跟原本的代碼一樣的，不過首先所有print的地方都加了個itchat.send來輸出日志，此外加了個帶鎖的狀態量running用來做運行開關。此外，部分參數是通過函數參數傳入的。
然后呢，寫了個itchat的handler
@itchat.msg_register([itchat.content.TEXT])
def chat_trigger(msg):
global lock, running, learning_rate, training_iters, batch_size, display_step
if msg['Text'] == u'開始':
print('Starting')
with lock:
run_state = running
if not run_state:
try:
threading.Thread(target=nn_train, args=(msg['FromUserName'], (learning_rate, training_iters, batch_size, display_step))).start()
except:
msg.reply('Running')
作用是，如果收到微信消息，內容為『開始』，那就跑訓練的函數（當然，為了防止阻塞，放在了另一個線程里）
最后再在腳本主流程里使用itchat登錄微信并且啟動itchat的服務，這樣就實現了基本的控制。
if __name__ == '__main__':
itchat.auto_login(hotReload=True)
itchat.run()
但是我們不滿足于此，我還希望可以對流程進行一些控制，對參數進行一些修改，于是乎：
@itchat.msg_register([itchat.content.TEXT])
def chat_trigger(msg):
global lock, running, learning_rate, training_iters, batch_size, display_step
if msg['Text'] == u'開始':
print('Starting')
with lock:
run_state = running
if not run_state:
try:
threading.Thread(target=nn_train, args=(msg['FromUserName'], (learning_rate, training_iters, batch_size, display_step))).start()
except:
msg.reply('Running')
elif msg['Text'] == u'停止':
print('Stopping')
with lock:
running = False
elif msg['Text'] == u'參數':
itchat.send('lr=%f, ti=%d, bs=%d, ds=%d'%(learning_rate, training_iters, batch_size, display_step),msg['FromUserName'])
else:
try:
param = msg['Text'].split()
key, value = param
print(key, value)
if key == 'lr':
learning_rate = float(value)
elif key == 'ti':
training_iters = int(value)
elif key == 'bs':
batch_size = int(value)
elif key == 'ds':
display_step = int(value)
except:
pass
通過這個，我們可以在epoch中途停止（因為nn_train里通過檢查running標志來確定是否需要停下來），也可以在訓練開始前調整learning_rate等幾個參數。
實在是很簡單……
雷峰網版權文章，未經授權禁止轉載。詳情見轉載須知。
