tensorflow2.0 - AttributeError : 'list' object has no attribute '_in_graph_mode' happens in optimizer. apply_gradients(grads_and_vars)

Question

我正在尝试使用 MNIST 数据集构建一个简单的全连接单隐藏层神经网络。

for epoch in range(training_epoch):
    for step in range(total_step):
        xs = x_train[step*batch_size:(step+1)*batch_size]
        ys = y_train[step*batch_size:(step+1)*batch_size]

        grads = grad(xs, ys, W, B)

        optimizer.apply_gradients(zip(grads, [W, B]))

W和B是tf.Variable类型:

Input_Dim = 784
H1_NN = 64
w1 = tf.Variable(tf.random.normal([Input_Dim, H1_NN], mean=0.0, stddev=1.), dtype=tf.float32)
b1 = tf.Variable(tf.zeros([H1_NN]), dtype=tf.float32)
Output_Dim = 10
w2 = tf.Variable(tf.random.normal([H1_NN, Output_Dim], mean=0.0, stddev=1.0), dtype=tf.float32)
b2 = tf.Variable(tf.zeros([Output_Dim]), dtype=tf.float32)
W = [w1, w2]
B = [b1, b2]enter code here

错误:

Traceback (most recent call last): File "C:/Users/HSNE_LP22B/PycharmProjects/浙大城市学院/mnist手写数字识别_1隐藏层.py", line 91, in optimizer.apply_gradients( grads_and_vars) File "C:\Users\HSNE_LP22B\Anaconda3\envs\TF2.1\lib\site-packages\tensorflow_core\python\keras\optimizer_v2\optimizer_v2.py", line 434, in apply_gradients self._create_slots(var_list) File "C:\Users\HSNE_LP22B\Anaconda3\envs\TF2.1\lib\site-packages\tensorflow_core\python\keras\optimizer_v2\adam.py", line 149, in _create_slots self.add_slot(var, 'm') File "C:\Users\HSNE_LP22B\Anaconda3\envs\TF2.1\lib\site-packages\tensorflow_core\python\keras\optimizer_v2\optimizer_v2.py", line 574, in add_slot var_key = _var_key(var) File "C:\Users\HSNE_LP22B\Anaconda3\envs\TF2.1\lib\site-packages\tensorflow_core\python\keras\optimizer_v2\optimizer_v2.py", line 1065, in _var_key if var._in_graph_mode: AttributeError: 'list' object has no attribute '_in_graph_mode'

我尝试使用 optimizer.apply_gradients(zip(grads, W+B))，但这种情况发生了

tensorflow.python.framework.errors_impl.InvalidArgumentError: Shapes of all inputs must match: values[0].shape = [784,64] != values[1].shape = [64,10] [Op:Pack] name: packed

Answer 1

import tensorflow as tf
import matplotlib.pyplot as plt

import numpy as np

mnist = tf.keras.datasets.mnist
(train_images, train_labels), (test_images, test_labels) = mnist.load_data()

total_num = len(train_images)  
valid_split = 0.2  
train_num = int(total_num*(1-valid_split))     
train_x = train_images[:train_num]       
train_y = train_labels[:train_num]

valid_x = train_images[train_num:]            
valid_y = train_labels[train_num:]

test_x = test_images
test_y = test_labels

train_x = train_x.reshape (-1,784)
valid_x = valid_x.reshape(-1,784)
test_x = test_x.reshape(-1,784)

train_x = tf.cast(train_x/255.0, tf.float32)
valid_x = tf.cast(valid_x/255.0, tf.float32)
test_x = tf.cast(test_x/255.0, tf.float32)

train_y = tf.one_hot(train_y,depth=10)
valid_y = tf.one_hot(valid_y,depth=10)
test_y = tf.one_hot(test_y, depth=10)

Input_Dim = 784
H1_NN = 64
W1 = tf.Variable(tf.random.normal([Input_Dim, H1_NN], mean=0.0, stddev=1.0, 
dtype=tf.float32))
B1 = tf.Variable(tf.zeros([H1_NN]), dtype = tf.float32)

Output_Dim = 10
W2 = tf.Variable(tf.random.normal([H1_NN, Output_Dim], mean=0.0, stddev=1.0, 
dtype=tf.float32))
B2 = tf.Variable(tf.zeros([Output_Dim]), dtype = tf.float32)

W = [W1, W2]
B = [B1, B2]

def model(x, w, b):
    x = tf. matmul(x, w[0]) + b[0]
    x = tf.nn.relu(x)
    x = tf.matmul(x, w[1]) + b[1]
    pred = tf.nn.softmax(x)
    return pred

def loss(x, y, w, b):
    pred = model(x, w, b)
    loss_ = tf.keras.losses.categorical_crossentropy(y_true=y, y_pred=pred)
    return tf.reduce_mean(loss_)

training_epochs = 20  
batch_size = 50  
learning_rate = 0.01  

def grad(x, y, w, b):
    with tf.GradientTape() as tape:
        loss_ = loss(x, y, w, b)
    return tape.gradient(loss_, [w[0],b[0],w[1],b[1]])

optimizer = tf.keras.optimizers.Adam(learning_rate=learning_rate)

def accuracy (x,y, w, b):
    pred = model(x, w, b) 

    correct_prediction = tf.equal(tf.argmax(pred,1), tf.argmax(y, 1))  

    return tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

steps = int(train_num / batch_size) 
loss_list_train = []  
loss_list_valid = [] 
acc_list_train = [] 
acc_list_valid = [] 

for epoch in range(training_epochs):
    for step in range(steps):
        xs = train_x[step * batch_size:(step + 1) * batch_size]
        ys = train_y[step * batch_size:(step + 1) * batch_size]
        grads = grad(xs, ys, W, B)  
        optimizer.apply_gradients(zip(grads, [W[0],B[0],W[1],B[1]]))

    loss_train = loss(train_x, train_y, W, B).numpy() 
    loss_valid = loss(valid_x, valid_y, W, B).numpy()
    acc_train = accuracy(train_x, train_y,W,B).numpy()
    acc_valid = accuracy(valid_x, valid_y, W, B).numpy()
    loss_list_train.append(loss_train)
    loss_list_valid.append(loss_valid)
    acc_list_train.append(acc_train)
    acc_list_valid.append(acc_valid)
    print("epoch={:3d}, train_loss={:.4f}, train_acc={:.4f}, val_loss={:.4f}, val_acc= 
{:.4f}".format(epoch + 1, loss_train, acc_train, loss_valid, acc_valid))