import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data tf.compat.v1.disable_eager_execution() #載入數據集 mnist=input_data.read_data_sets("MNIST_data",one_hot=True) #每一個批次大小 batch_size=100 #計算一共有多少個批次 n_bath=mnist.train.num_examples // batch_size print(n_bath) with tf.name_scope('input'): #定義兩個placeholder x=tf.compat.v1.placeholder(tf.float32,[None,784],name='x-input') y=tf.compat.v1.placeholder(tf.float32,[None,10],name='y-input') with tf.name_scope('layer'): #建立一個簡單的神經網絡 with tf.name_scope('wights'): W=tf.Variable(tf.zeros([784,10]),name='W') with tf.name_scope('biases'): b=tf.Variable(tf.zeros([10]),name='b') with tf.name_scope('wx_plus_b'): wx_plus_b=tf.matmul(x,W)+b with tf.name_scope('softmax'): prediction=tf.nn.softmax(wx_plus_b) with tf.name_scope('loss'): #二次代價函數 loss=tf.reduce_mean(tf.square(y-prediction)) with tf.name_scope('train'): #梯度降低 train_step=tf.compat.v1.train.GradientDescentOptimizer(0.2).minimize(loss) #初始化變量 init=tf.compat.v1.global_variables_initializer() with tf.name_scope('accuracy'): with tf.name_scope('correct_prediction'): #結果存放在一個布爾型列表中 #返回的是一系列的True或False argmax返回一維張量中最大的值所在的位置,對比兩個最大位置是否一致 correct_prediction=tf.equal(tf.argmax(y,1),tf.argmax(prediction,1)) with tf.name_scope('accuracy'): #求準確率 #cast:將布爾類型轉換爲float,將True爲1.0,False爲0,而後求平均值 accuracy=tf.reduce_mean(tf.cast(correct_prediction,tf.float32)) with tf.compat.v1.Session() as sess: sess.run(init) writer=tf.compat.v1.summary.FileWriter('logs/',sess.graph) for epoch in range(1): for batch in range(n_bath): #得到一批次的數據,batch_xs爲圖片,batch_ys爲圖片標籤 batch_xs,batch_ys=mnist.train.next_batch(batch_size) #進行訓練 sess.run(train_step,feed_dict={x:batch_xs,y:batch_ys}) #訓練完一遍後,測試下準確率的變化 acc=sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels}) print("Iter "+str(epoch)+",Testing Accuracy "+str(acc))
會生成logs/目錄,而且目錄下的文件咱們須要這樣子打開python
點擊對應的模塊,會展現詳細的數據信息以及相應的結構展現瀏覽器