無法將函數轉換爲張量或操作

Question

我不斷收到我正在構建的卷積網絡的錯誤，我不知道爲什麼錯誤會彈出。這裏是我的網絡：

learning_rate = 0.0001 
epochs = 10 
batch_size = 128 
test_valid_size = 128 
n_classes = 5 
dropout = 0.75 

start1 = timer() 

with tf.device('/gpu:0'): 
    weights = { 
    'wc1': tf.Variable(tf.random_normal([5, 5, 1, 32])), 
    'wc2': tf.Variable(tf.random_normal([5, 5, 32, 64])), 
    'wd1': tf.Variable(tf.random_normal([7*7*64, 1024])), 
    '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]))} 

    x = tf.placeholder(tf.float32, [None, 80, 240, 1]) 
    y = tf.placeholder(tf.float32, [None, n_classes]) 
    keep_prob = tf.placeholder(tf.float32) 

    layer_1 = tf.nn.conv2d(x, weights['wc1'], strides = [1, 1, 1, 1], padding = 'SAME') 
    layer_1 = tf.nn.bias_add(layer_1, biases['bc1']) 
    layer_1 = tf.nn.max_pool(layer_1, ksize = [1, 2, 2, 1], strides = [1, 2, 2, 1], padding = 'SAME') 

    layer_2 = tf.nn.conv2d(layer_1, weights['wc2'], strides = [1, 1, 1, 1], padding = 'SAME') 
    layer_2 = tf.nn.bias_add(layer_2, biases['bc2']) 
    layer_2 = tf.nn.max_pool(layer_2, ksize = [1, 2, 2, 1], strides = [1, 2, 2, 1], padding = 'SAME') 

    layer_3 = tf.reshape(layer_2, [-1, weights['wd1'].get_shape().as_list()[0]]) 
    layer_3 = tf.add(tf.matmul(layer_3, weights['wd1']), biases['bd1']) 
    layer_3 = tf.nn.relu(layer_3) 
    layer_3 = tf.nn.dropout(layer_3, dropout) 

    logits = tf.add(tf.matmul(layer_3, weights['out']), biases['out']) 

    cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits = logits, labels = y)) 
    optimizer = tf.train.GradientDescentOptimizer(learning_rate = learning_rate).minimize(cost) 

    correct_pred = tf.equal(tf.argmax(logits, 1), tf.argmax(y, 1)) 
    accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32)) 

init = tf.global_variables_initializer 

save_file_2 = './train_model2.ckpt' 
saver = tf.train.Saver() 

with tf.Session() as sess: 
    sess.run(init) 

    for epoch in range(epochs): 
     for batch_features, batch_labels in batches(batch_size, count_X_train, count_y_train): 
      sess.run(optimizer, feed_dict = {x:batch_features, y:batch_labels, keep_prob:dropout}) 

    saver.save(sess, save_file_2) 
    print("") 
    print("trained model_2 saved") 

    test_acc = sess.run(accuracy, feed_dict = {x: count_X_test[:test_valid_size], y: count_y_test[:test_valid_size], keep_prob:1.}) 
    print('Testing Accuracy: {}'.format(test_acc)) 


end1 = timer() 
print("time:", str(end1 - start1)) 

某處的代碼，我猜sess.run（INIT）是給我下面的錯誤：

TypeError: Fetch argument <function global_variables_initializer at 0x00000224FD81FD90> has invalid type <class 'function'>, must be a string or Tensor. (Can not convert a function into a Tensor or Operation.) 

任何想法，這個錯誤可能來自哪裏？謝謝！

Answer 1

糟糕。原來我只是需要改變

init = tf.global_variables_initializer 

到

init = tf.global_variables_initializer()