如何修复MatMul Op的float64类型与float32 TypeError类型不匹配？

Question

我正在尝试将Nueral Network权重保存到文件中，然后通过初始化网络而不是随机初始化来恢复这些权重。随机初始化我的代码工作正常。但是，当我从文件初始化权重时，它显示错误TypeError: Input 'b' of 'MatMul' Op has type float64 that does not match type float32 of argument 'a'.我不知道如何解决这个问题。这是我的代码：

模型初始化

# Parameters
training_epochs = 5
batch_size = 64
display_step = 5
batch = tf.Variable(0, trainable=False)
regualarization =  0.008

# Network Parameters
n_hidden_1 = 300 # 1st layer num features
n_hidden_2 = 250 # 2nd layer num features

n_input = model.layer1_size # Vector input (sentence shape: 30*10)
n_classes = 12 # Sentence Category detection total classes (0-11 categories)

#History storing variables for plots
loss_history = []
train_acc_history = []
val_acc_history = []

# tf Graph input
x = tf.placeholder("float", [None, n_input])
y = tf.placeholder("float", [None, n_classes])

模型参数

#loading Weights
def weight_variable(fan_in, fan_out, filename):
    stddev = np.sqrt(2.0/fan_in)
    if (filename == ""):
        initial  = tf.random_normal([fan_in,fan_out], stddev=stddev)
    else:
        initial  = np.loadtxt(filename)
    print initial.shape
    return tf.Variable(initial)

#loading Biases
def bias_variable(shape, filename):
    if (filename == ""):
     initial = tf.constant(0.1, shape=shape)
    else:
     initial  = np.loadtxt(filename)  
    print initial.shape
    return tf.Variable(initial)

# Create model
def multilayer_perceptron(_X, _weights, _biases):
    layer_1 = tf.nn.relu(tf.add(tf.matmul(_X, _weights['h1']), _biases['b1'])) 
    layer_2 = tf.nn.relu(tf.add(tf.matmul(layer_1, _weights['h2']), _biases['b2'])) 
    return tf.matmul(layer_2, weights['out']) + biases['out']  

# Store layers weight & bias
weights = {
'h1':  w2v_utils.weight_variable(n_input, n_hidden_1,    filename="weights_h1.txt"),
'h2':  w2v_utils.weight_variable(n_hidden_1, n_hidden_2, filename="weights_h2.txt"),
'out': w2v_utils.weight_variable(n_hidden_2, n_classes,  filename="weights_out.txt") 
}

 biases = {
'b1': w2v_utils.bias_variable([n_hidden_1], filename="biases_b1.txt"),
'b2': w2v_utils.bias_variable([n_hidden_2], filename="biases_b2.txt"),
'out': w2v_utils.bias_variable([n_classes], filename="biases_out.txt")
}

# Define loss and optimizer
#learning rate
# Optimizer: set up a variable that's incremented once per batch and
# controls the learning rate decay.
learning_rate = tf.train.exponential_decay(
    0.02*0.01,           # Base learning rate. #0.002
    batch * batch_size,  # Current index into the dataset.
    X_train.shape[0],    # Decay step.
    0.96,                # Decay rate.
    staircase=True)


# Construct model
pred = tf.nn.relu(multilayer_perceptron(x, weights, biases))

#L2 regularization
l2_loss = tf.add_n([tf.nn.l2_loss(v) for v in tf.trainable_variables()])

#Softmax loss
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y)) 

#Total_cost
cost = cost+ (regualarization*0.5*l2_loss)

# Adam Optimizer
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost,global_step=batch)


# Add ops to save and restore all the variables.
saver = tf.train.Saver()

# Initializing the variables
init = tf.initialize_all_variables()

print "Network Initialized!"

错误详情

Answer 1

tf.matmul() op不执行自动类型转换，因此它的两个输入必须具有相同的元素类型。您看到的错误消息表明您调用tf.matmul()，其中第一个参数的类型为tf.float32，第二个参数的类型为tf.float64。您必须转换其中一个输入以匹配另一个输入，例如使用tf.cast(x, tf.float32)。

查看代码，我没有看到任何显式创建tf.float64张量的地方（TensorFlow Python API中浮点值的默认dtype - 例如{{1} } -is tf.constant(37.0)）。我猜这些错误是由tf.float32调用引起的，这些调用可能正在加载np.loadtxt(filename)数组。您可以显式更改它们以加载np.float64数组（转换为np.float32张量），如下所示：

tf.float32

Answer 2

虽然这是一个老问题，但我希望你包括我遇到了同样的问题。我使用dtype=tf.float64进行参数初始化以及创建X和Y占位符来解决它。

这是我的代码的快照。

X = tf.placeholder(shape=[n_x, None],dtype=tf.float64)
Y = tf.placeholder(shape=[n_y, None],dtype=tf.float64)

和

parameters['W' + str(l)] = tf.get_variable('W' + str(l), [layers_dims[l],layers_dims[l-1]],dtype=tf.float64, initializer = tf.contrib.layers.xavier_initializer(seed = 1))
parameters['b' + str(l)] = tf.get_variable('b' + str(l), [layers_dims[l],1],dtype=tf.float64, initializer = tf.zeros_initializer())

使用float64数据类型声明所有placholders和参数将解决此问题。

Answer 3

对于Tensorflow 2

您可以转换张量之一，例如：

_X = tf.cast(_X, dtype='float64')