我的卷积神经网络编码模型如下： 当我使用整个输入示例时，您将在下面找到代码。 因此，正在工作的小批量代码。我看不出有什么区别！
# model
def model(train_x, train_y, test_x, test_y, learning_rate = 0.009,
num_iterations = 100, print_cost = True):
"""
Implements a three-layer ConvNet in Tensorflow:
CONV2D -> RELU -> MAXPOOL -> CONV2D -> RELU -> MAXPOOL -> FLATTEN -> FULLYCONNECTED
Arguments:
X_train -- training set, of shape (None, 64, 64, 3)
Y_train -- test set, of shape (None, n_y = 6)
X_test -- training set, of shape (None, 64, 64, 3)
Y_test -- test set, of shape (None, n_y = 6)
learning_rate -- learning rate of the optimization
num_epochs -- number of epochs of the optimization loop
minibatch_size -- size of a minibatch
print_cost -- True to print the cost every 100 epochs
Returns:
train_accuracy -- real number, accuracy on the train set (X_train)
test_accuracy -- real number, testing accuracy on the test set (X_test)
parameters -- parameters learnt by the model. They can then be used to predict.
"""
ops.reset_default_graph() # to be able to rerun the model without overwriting tf variables
tf.set_random_seed(1) # to keep results consistent (tensorflow seed)
seed = 3 # to keep results consistent (numpy seed)
(m, n_H0, n_W0, n_C0) = train_x.shape
n_y = train_y.shape[1]
costs = [] # To keep track of the cost
# Create Placeholders of the correct shape
### START CODE HERE ### (1 line)
X, Y = create_placeholders(n_H0, n_W0, n_C0, n_y)
### END CODE HERE ###
# Initialize parameters
### START CODE HERE ### (1 line)
parameters = initialize_parameters()
### END CODE HERE ###
for i in range(0, num_iterations):
# Forward propagation: Build the forward propagation in the tensorflow graph
### START CODE HERE ### (1 line)
Z3 = forward_propagation(X, parameters)
### END CODE HERE ###
# Cost function: Add cost function to tensorflow graph
### START CODE HERE ### (1 line)
cost = compute_cost(Z3, Y)
### END CODE HERE ###
# Backpropagation: Define the tensorflow optimizer. Use an AdamOptimizer that minimizes the cost.
### START CODE HERE ### (1 line)
optimizer = tf.train.AdamOptimizer(learning_rate = learning_rate).minimize(cost)
### END CODE HERE ###
# Initialize all the variables globally
init = tf.global_variables_initializer()
# Start the session to compute the tensorflow graph
with tf.Session() as sess:
# Run the initialization
sess.run(init)
# Do the training loop
_ , temp_cost = sess.run([optimizer, cost], feed_dict = {X: train_x, Y: train_y})
### END CODE HERE ###
# Print the cost every 5 itterrations
print("cost =" +str(cost))
if print_cost == True and i % 5 == 0:
print ("Cost after num_iterations %i: %f" % (i, cost))
if print_cost == True and i % 1 == 0:
costs.append(cost)
# plot the cost
plt.plot(np.squeeze(costs))
plt.ylabel('cost')
plt.xlabel('iterations (per tens)')
plt.title("Learning rate =" + str(learning_rate))
plt.show()
# Calculate the correct predictions
predict_op = tf.argmax(Z3, 1)
correct_prediction = tf.equal(predict_op, tf.argmax(Y, 1))
# Calculate accuracy on the test set
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
print(accuracy)
train_accuracy = accuracy.eval({X: train_x, Y: train_y})
test_accuracy = accuracy.eval({X: test_x, Y: test_y})
print("Train Accuracy:", train_accuracy)
print("Test Accuracy:", test_accuracy)
return train_accuracy, test_accuracy, parameters
However when I call the function model via
_, _, parameters = model(train_x, train_y, test_x, test_y)
I run into following error:
cost =Tensor("Mean:0", shape=(), dtype=float32)
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-78-8bde5fad21ba> in <module>()
----> 1 _, _, parameters = model(train_x, train_y, test_x, test_y)
<ipython-input-77-68bdfb51274c> in model(train_x, train_y, test_x, test_y, learning_rate, num_iterations, print_cost)
73 print("cost =" +str(cost))
74 if print_cost == True and i % 5 == 0:
---> 75 print ("Cost after num_iterations %i: %f" % (i, cost))
76 if print_cost == True and i % 1 == 0:
77 costs.append(cost)
TypeError: must be real number, not Tensor
Can somebody explain me how to resolve this error?
我的小批量代码正在工作：添加了此代码，以便您可以看到它正在工作。我看不出上面的代码有什么区别，以及为什么上面的代码不起作用。也许你可以帮我。嘟嘟
# GRADED FUNCTION: model
def model(train_x, train_y, test_x, test_y, learning_rate = 0.009,
num_epochs = 50, minibatch_size = 64, print_cost = True):
"""
Implements a three-layer ConvNet in Tensorflow:
CONV2D -> RELU -> MAXPOOL -> CONV2D -> RELU -> MAXPOOL -> FLATTEN -> FULLYCONNECTED
Arguments:
X_train -- training set, of shape (None, 64, 64, 3)
Y_train -- test set, of shape (None, n_y = 6)
X_test -- training set, of shape (None, 64, 64, 3)
Y_test -- test set, of shape (None, n_y = 6)
learning_rate -- learning rate of the optimization
num_epochs -- number of epochs of the optimization loop
minibatch_size -- size of a minibatch
print_cost -- True to print the cost every 100 epochs
Returns:
train_accuracy -- real number, accuracy on the train set (X_train)
test_accuracy -- real number, testing accuracy on the test set (X_test)
parameters -- parameters learnt by the model. They can then be used to predict.
"""
ops.reset_default_graph() # to be able to rerun the model without overwriting tf variables
tf.set_random_seed(1) # to keep results consistent (tensorflow seed)
seed = 3 # to keep results consistent (numpy seed)
(m, n_H0, n_W0, n_C0) = train_x.shape
n_y = train_y.shape[1]
costs = [] # To keep track of the cost
# Create Placeholders of the correct shape
### START CODE HERE ### (1 line)
X, Y = create_placeholders(n_H0, n_W0, n_C0, n_y)
### END CODE HERE ###
# Initialize parameters
### START CODE HERE ### (1 line)
parameters = initialize_parameters()
### END CODE HERE ###
# Forward propagation: Build the forward propagation in the tensorflow graph
### START CODE HERE ### (1 line)
Z3 = forward_propagation(X, parameters)
### END CODE HERE ###
# Cost function: Add cost function to tensorflow graph
### START CODE HERE ### (1 line)
cost = compute_cost(Z3, Y)
### END CODE HERE ###
# Backpropagation: Define the tensorflow optimizer. Use an AdamOptimizer that minimizes the cost.
### START CODE HERE ### (1 line)
optimizer = tf.train.AdamOptimizer(learning_rate = learning_rate).minimize(cost)
### END CODE HERE ###
# Initialize all the variables globally
init = tf.global_variables_initializer()
# Start the session to compute the tensorflow graph
with tf.Session() as sess:
# Run the initialization
sess.run(init)
# Do the training loop
for epoch in range(num_epochs):
#print("m = " + str(m))
minibatch_cost = 0.
num_minibatches = int(m / minibatch_size) # number of minibatches of size minibatch_size in the train set
#print(" minibatch_size =" + str(minibatch_size))
seed = seed + 1
minibatches = random_mini_batches(train_x, train_y, minibatch_size, seed)
#print("minibatch =" + str(minibatch))
#print("minibatches = " + str(minibatches))
for minibatch in minibatches:
# Select a minibatch
(minibatch_X, minibatch_Y) = minibatch
# IMPORTANT: The line that runs the graph on a minibatch.
# Run the session to execute the optimizer and the cost, the feedict should contain a minibatch for (X,Y).
### START CODE HERE ### (1 line)
_ , temp_cost = sess.run([optimizer, cost], feed_dict = {X: minibatch_X, Y: minibatch_Y})
### END CODE HERE ###
minibatch_cost += temp_cost / num_minibatches
# Print the cost every 5 epoch
if print_cost == True and epoch % 5 == 0:
print ("Cost after epoch %i: %f" % (epoch, minibatch_cost))
if print_cost == True and epoch % 1 == 0:
costs.append(minibatch_cost)
# plot the cost
plt.plot(np.squeeze(costs))
plt.ylabel('cost')
plt.xlabel('iterations (per tens)')
plt.title("Learning rate =" + str(learning_rate))
plt.show()
# Calculate the correct predictions
predict_op = tf.argmax(Z3, 1)
correct_prediction = tf.equal(predict_op, tf.argmax(Y, 1))
# Calculate accuracy on the test set
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
print(accuracy)
train_accuracy = accuracy.eval({X: train_x, Y: train_y})
test_accuracy = accuracy.eval({X: test_x, Y: test_y})
print("Train Accuracy:", train_accuracy)
print("Test Accuracy:", test_accuracy)
return train_accuracy, test_accuracy, parameters
在输出下方：
_, _, parameters = model(X_train, Y_train, X_test, Y_test)
Cost after epoch 0: 1.917929
Cost after epoch 5: 1.506757
Cost after epoch 10: 0.955359
Cost after epoch 15: 0.845802
Cost after epoch 20: 0.701174
Cost after epoch 25: 0.571977
Cost after epoch 30: 0.518435
Cost after epoch 35: 0.495806
Cost after epoch 40: 0.429827
Cost after epoch 45: 0.407291
第 73 行已经损坏。要打印张量，您需要使用tf.Print， 但这需要你把它添加到你的计算图中：
print_node = tf.Print(opt.get_slot(var,'m'), [opt.get_slot(var,'m')], 'm')
sess.run([print_node], ...)
问题解决了。 将迭代for i in range(0, num_iterations):
在行之前_ , temp_cost = sess.run([optimizer, cost], feed_dict = {X: train_x, Y: train_y})
而不是在我的前进传播步骤之前！