Tensorflow怎么訓練MNIST手寫數字識別模型

今天就跟大家聊聊有關Tensorflow怎么訓練MNIST手寫數字識別模型，可能很多人都不太了解，為了讓大家更加了解，小編給大家總結了以下內容，希望大家根據這篇文章可以有所收獲。

import tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_dataINPUT_NODE = 784  # 輸入層節點=圖片像素=28x28=784OUTPUT_NODE = 10  # 輸出層節點數=圖片類別數目LAYER1_NODE = 500  # 隱藏層節點數，只有一個隱藏層BATCH_SIZE = 100  # 一個訓練包中的數據個數，數字越小          # 越接近隨機梯度下降，越大越接近梯度下降LEARNING_RATE_BASE = 0.8   # 基礎學習率LEARNING_RATE_DECAY = 0.99  # 學習率衰減率REGULARIZATION_RATE = 0.0001  # 正則化項系數TRAINING_STEPS = 30000     # 訓練輪數MOVING_AVG_DECAY = 0.99    # 滑動平均衰減率# 定義一個輔助函數，給定神經網絡的輸入和所有參數，計算神經網絡的前向傳播結果def inference(input_tensor, avg_class, weights1, biases1,       weights2, biases2): # 當沒有提供滑動平均類時，直接使用參數當前取值 if avg_class == None:  # 計算隱藏層前向傳播結果  layer1 = tf.nn.relu(tf.matmul(input_tensor, weights1) + biases1)  # 計算輸出層前向傳播結果  return tf.matmul(layer1, weights2) + biases2 else:  # 首先計算變量的滑動平均值，然后計算前向傳播結果  layer1 = tf.nn.relu(    tf.matmul(input_tensor, avg_class.average(weights1)) +    avg_class.average(biases1))  return tf.matmul(    layer1, avg_class.average(weights2)) + avg_class.average(biases2)# 訓練模型的過程def train(mnist): x = tf.placeholder(tf.float32, [None, INPUT_NODE], name='x-input') y_ = tf.placeholder(tf.float32, [None, OUTPUT_NODE], name='y-input') # 生成隱藏層參數 weights1 = tf.Variable(   tf.truncated_normal([INPUT_NODE, LAYER1_NODE], stddev=0.1)) biases1 = tf.Variable(tf.constant(0.1, shape=[LAYER1_NODE])) # 生成輸出層參數 weights2 = tf.Variable(   tf.truncated_normal([LAYER1_NODE, OUTPUT_NODE], stddev=0.1)) biases2 = tf.Variable(tf.constant(0.1, shape=[OUTPUT_NODE])) # 計算前向傳播結果，不使用參數滑動平均值 avg_class=None y = inference(x, None, weights1, biases1, weights2, biases2) # 定義訓練輪數變量，指定為不可訓練 global_step = tf.Variable(0, trainable=False) # 給定滑動平均衰減率和訓練輪數的變量，初始化滑動平均類 variable_avgs = tf.train.ExponentialMovingAverage(   MOVING_AVG_DECAY, global_step) # 在所有代表神經網絡參數的可訓練變量上使用滑動平均 variables_avgs_op = variable_avgs.apply(tf.trainable_variables()) # 計算使用滑動平均值后的前向傳播結果 avg_y = inference(x, variable_avgs, weights1, biases1, weights2, biases2) # 計算交叉熵作為損失函數 cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(   logits=y, labels=tf.argmax(y_, 1)) cross_entropy_mean = tf.reduce_mean(cross_entropy) # 計算L2正則化損失函數 regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE) regularization = regularizer(weights1) + regularizer(weights2) loss = cross_entropy_mean + regularization # 設置指數衰減的學習率 learning_rate = tf.train.exponential_decay(   LEARNING_RATE_BASE,   global_step,              # 當前迭代輪數   mnist.train.num_examples / BATCH_SIZE, # 過完所有訓練數據的迭代次數   LEARNING_RATE_DECAY) # 優化損失函數 train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(   loss, global_step=global_step) # 反向傳播同時更新神經網絡參數及其滑動平均值 with tf.control_dependencies([train_step, variables_avgs_op]):  train_op = tf.no_op(name='train') # 檢驗使用了滑動平均模型的神經網絡前向傳播結果是否正確 correct_prediction = tf.equal(tf.argmax(avg_y, 1), tf.argmax(y_, 1)) accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) # 初始化會話并開始訓練 with tf.Session() as sess:  tf.global_variables_initializer().run()  # 準備驗證數據，用于判斷停止條件和訓練效果  validate_feed = {x: mnist.validation.images,          y_: mnist.validation.labels}  # 準備測試數據，用于模型優劣的最后評價標準  test_feed = {x: mnist.test.images, y_: mnist.test.labels}  # 迭代訓練神經網絡  for i in range(TRAINING_STEPS):   if i%1000 == 0:    validate_acc = sess.run(accuracy, feed_dict=validate_feed)    print("After %d training step(s), validation accuracy using average "       "model is %g " % (i, validate_acc))   xs, ys = mnist.train.next_batch(BATCH_SIZE)   sess.run(train_op, feed_dict={x: xs, y_: ys})  # 訓練結束后在測試集上檢測模型的最終正確率  test_acc = sess.run(accuracy, feed_dict=test_feed)  print("After %d training steps, test accuracy using average model "     "is %g " % (TRAINING_STEPS, test_acc))# 主程序入口def main(argv=None): mnist = input_data.read_data_sets("/tmp/data", one_hot=True) train(mnist)# Tensorflow主程序入口if __name__ == '__main__': tf.app.run()

輸出結果如下：

Extracting /tmp/data/train-images-idx3-ubyte.gzExtracting /tmp/data/train-labels-idx1-ubyte.gzExtracting /tmp/data/t10k-images-idx3-ubyte.gzExtracting /tmp/data/t10k-labels-idx1-ubyte.gzAfter 0 training step(s), validation accuracy using average model is 0.0462After 1000 training step(s), validation accuracy using average model is 0.9784After 2000 training step(s), validation accuracy using average model is 0.9806After 3000 training step(s), validation accuracy using average model is 0.9798After 4000 training step(s), validation accuracy using average model is 0.9814After 5000 training step(s), validation accuracy using average model is 0.9826After 6000 training step(s), validation accuracy using average model is 0.9828After 7000 training step(s), validation accuracy using average model is 0.9832After 8000 training step(s), validation accuracy using average model is 0.9838After 9000 training step(s), validation accuracy using average model is 0.983After 10000 training step(s), validation accuracy using average model is 0.9836After 11000 training step(s), validation accuracy using average model is 0.9822After 12000 training step(s), validation accuracy using average model is 0.983After 13000 training step(s), validation accuracy using average model is 0.983After 14000 training step(s), validation accuracy using average model is 0.9844After 15000 training step(s), validation accuracy using average model is 0.9832After 16000 training step(s), validation accuracy using average model is 0.9844After 17000 training step(s), validation accuracy using average model is 0.9842After 18000 training step(s), validation accuracy using average model is 0.9842After 19000 training step(s), validation accuracy using average model is 0.9838After 20000 training step(s), validation accuracy using average model is 0.9834After 21000 training step(s), validation accuracy using average model is 0.9828After 22000 training step(s), validation accuracy using average model is 0.9834After 23000 training step(s), validation accuracy using average model is 0.9844After 24000 training step(s), validation accuracy using average model is 0.9838After 25000 training step(s), validation accuracy using average model is 0.9834After 26000 training step(s), validation accuracy using average model is 0.984After 27000 training step(s), validation accuracy using average model is 0.984After 28000 training step(s), validation accuracy using average model is 0.9836After 29000 training step(s), validation accuracy using average model is 0.9842After 30000 training steps, test accuracy using average model is 0.9839

看完上述內容，你們對Tensorflow怎么訓練MNIST手寫數字識別模型有進一步的了解嗎？如果還想了解更多知識或者相關內容，請關注億速云行業資訊頻道，感謝大家的支持。