注意这里是将训练好的神经网络拿出来进行预测（使用），而不是测试，测试可与训练在一个文件中进行，当然也可像这样载入网络和训练数据来测试。
tensorflow_tutorial.py文件---训练神经网络
#!/usr/bin/env python
# coding=utf-8
import math
import numpy as np
import h5py
import matplotlib.pyplot as plt
import tensorflow as tf
from tensorflow.python.framework import ops
from tf_utils import load_dataset, random_mini_batches, convert_to_one_hot, predict
import scipy
from PIL import Image
from scipy import ndimage
# Loading the dataset
X_train_orig, Y_train_orig, X_test_orig, Y_test_orig, classes = load_dataset()
# Flatten the training and test images
X_train_flatten = X_train_orig.reshape(X_train_orig.shape[0], -1).T
X_test_flatten = X_test_orig.reshape(X_test_orig.shape[0], -1).T
# Normalize image vectors
X_train = X_train_flatten/255.
X_test = X_test_flatten/255.
# Convert training and test labels to one hot matrices,每一列代表一张图片label的ont hot vector
Y_train = convert_to_one_hot(Y_train_orig, 6)
Y_test = convert_to_one_hot(Y_test_orig, 6)
def create_placeholders(n_x, n_y):
"""
Creates the placeholders for the tensorflow session.
Arguments:
n_x -- scalar, size of an image vector (num_px * num_px = 64 * 64 * 3 = 12288)
n_y -- scalar, number of classes (from 0 to 5, so -> 6)
Returns:
X -- placeholder for the data input, of shape [n_x, None] and dtype "float"
Y -- placeholder for the input labels, of shape [n_y, None] and dtype "float"
Tips:
- You will use None because it let's us be flexible on the number of examples you will for the placeholders.
In fact, the number of examples during test/train is different.
"""
### START CODE HERE ### (approx. 2 lines)
X = tf.placeholder(tf.float32,shape=(n_x,None))
Y = tf.placeholder(tf.float32,shape=(n_y,None))
### END CODE HERE ###
return X, Y
def get_weight(shape):
w=tf.Variable(tf.truncated_normal(shape,stddev=0.1))
return w
def get_bias(shape):
b=tf.Variable(tf.zeros(shape))
return b
def initialize_parameters():
"""
Initializes parameters to build a neural network with tensorflow. The shapes are:
W1 : [25, 12288]
b1 : [25, 1]
W2 : [12, 25]
b2 : [12, 1]
W3 : [6, 12]
b3 : [6, 1]
Returns:
parameters -- a dictionary of tensors containing W1, b1, W2, b2, W3, b3
"""
tf.set_random_seed(1) # so that your "random" numbers match ours
### START CODE HERE ### (approx. 6 lines of code)
W1 = get_weight([25,12288])
b1 = get_bias([25,1])
W2 = get_weight([12,25])
b2 = get_bias([12,1])
W3 = get_weight([6,12])
b3 = get_bias([6,1])
### END CODE HERE ###
parameters = {"W1": W1,
"b1": b1,
"W2": W2,
"b2": b2,
"W3": W3,
"b3": b3}
return parameters
def forward_propagation(X, parameters):
"""
Implements the forward propagation for the model: LINEAR -> RELU -> LINEAR -> RELU -> LINEAR -> SOFTMAX
Arguments:
X -- input dataset placeholder, of shape (input size, number of examples)
parameters -- python dictionary containing your parameters "W1", "b1", "W2", "b2", "W3", "b3"
the shapes are given in initialize_parameters
Returns:
Z3 -- the output of the last LINEAR unit
"""
# Retrieve the parameters from the dictionary "parameters"
W1 = parameters['W1']
b1 = parameters['b1']
W2 = parameters['W2']
b2 = parameters['b2']
W3 = parameters['W3']
b3 = parameters['b3']
### START CODE HERE ### (approx. 5 lines) # Numpy Equivalents:
Z1 = tf.matmul(W1,X)+b1 # Z1 = np.dot(W1, X) + b1
A1 = tf.nn.relu(Z1) # A1 = relu(Z1)
Z2 = tf.matmul(W2,A1)+b2 # Z2 = np.dot(W2, a1) + b2
A2 = tf.nn.relu(Z2) # A2 = relu(Z2)
Z3 = tf.matmul(W3,A2)+b3 # Z3 = np.dot(W3,Z2) + b3
### END CODE HERE ###
return Z3
# GRADED FUNCTION: compute_cost
def compute_cost(Z3, Y):
"""
Computes the cost
Arguments:
Z3 -- output of forward propagation (output of the last LINEAR unit), of shape (6, number of examples)
Y -- "true" labels vector placeholder, same shape as Z3
Returns:
cost - Tensor of the cost function
"""
# to fit the tensorflow requirement for tf.nn.softmax_cross_entropy_with_logits(...,...)
logits = tf.transpose(Z3)
labels = tf.transpose(Y)
### START CODE HERE ### (1 line of code)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits = logits, labels = labels))
### END CODE HERE ###
return cost
def model(X_train, Y_train, X_test, Y_test, learning_rate=0.0001,
num_epochs=1500, minibatch_size=32, print_cost=True):
"""
Implements a three-layer tensorflow neural network: LINEAR->RELU->LINEAR->RELU->LINEAR->SOFTMAX.
Arguments:
X_train -- training set, of shape (input size = 12288, number of training examples = 1080)
Y_train -- test set, of shape (output size = 6, number of training examples = 1080)
X_test -- training set, of shape (input size = 12288, number of training examples = 120)
Y_test -- test set, of shape (output size = 6, number of test examples = 120)
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:
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 consistent results
seed = 3 # to keep consistent results
(n_x, m) = X_train.shape # (n_x: input size, m : number of examples in the train set)
n_y = Y_train.shape[0] # n_y : output size
costs = [] # To keep track of the cost
# Create Placeholders of shape (n_x, n_y)
### START CODE HERE ### (1 line)
X, Y = create_placeholders(n_x,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.
### START CODE HERE ### (1 line)
optimizer = tf.train.AdamOptimizer(learning_rate).minimize(cost)
### END CODE HERE ###
# Initialize all the variables
init = tf.global_variables_initializer()
# 实例化Saver对象，max_to_keep=1表示只想保存最终模型
# 默认max_to_keep=5，保存最近的5个模型
saver=tf.train.Saver(max_to_keep=1)
# 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):
epoch_cost = 0. # Defines a cost related to an epoch
num_minibatches = int(m / minibatch_size) # number of minibatches of size minibatch_size in the train set
seed = seed + 1
# 将总的训练数据随机分成m/minibatch_size个minibatch
# 由于每个epoch的随机种子在递增（都不同了），所以每个epoch的训练数据的划分是不同的
minibatches = random_mini_batches(X_train, Y_train, minibatch_size, seed)
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)
_, minibatch_cost = sess.run((optimizer,cost),feed_dict={X:minibatch_X,Y:minibatch_Y})
### END CODE HERE ###
epoch_cost += minibatch_cost / num_minibatches
saver.save(sess,'./model/my_model',global_step=num_epochs)
# Print the cost every epoch
if print_cost == True and epoch % 100 == 0:
print("Cost after epoch %i: %f" % (epoch, epoch_cost))
if print_cost == True and epoch % 5 == 0:
costs.append(epoch_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()
# lets save the parameters in a variable
print("Parameters have been trained!")
# Calculate the correct predictions
correct_prediction = tf.equal(tf.argmax(Z3), tf.argmax(Y))
# Calculate accuracy on the test set
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
print("Train Accuracy:", accuracy.eval({X: X_train, Y: Y_train}))
print("Test Accuracy:", accuracy.eval({X: X_test, Y: Y_test}))
if __name__ == '__main__':
model(X_train, Y_train, X_test, Y_test)
tf_utils.py----辅助训练神经网络的文件
import h5py
import numpy as np
import tensorflow as tf
import math
def load_dataset():
train_dataset = h5py.File('datasets/train_signs.h5', "r")
train_set_x_orig = np.array(train_dataset["train_set_x"][:]) # your train set features
train_set_y_orig = np.array(train_dataset["train_set_y"][:]) # your train set labels
test_dataset = h5py.File('datasets/test_signs.h5', "r")
test_set_x_orig = np.array(test_dataset["test_set_x"][:]) # your test set features
test_set_y_orig = np.array(test_dataset["test_set_y"][:]) # your test set labels
classes = np.array(test_dataset["list_classes"][:]) # the list of classes
train_set_y_orig = train_set_y_orig.reshape((1, train_set_y_orig.shape[0]))
test_set_y_orig = test_set_y_orig.reshape((1, test_set_y_orig.shape[0]))
return train_set_x_orig, train_set_y_orig, test_set_x_orig, test_set_y_orig, classes
def random_mini_batches(X, Y, mini_batch_size = 64, seed = 0):
m = X.shape[1] # number of training examples
mini_batches = []
np.random.seed(seed)
# Step 1: Shuffle (X, Y)
permutation = list(np.random.permutation(m))
shuffled_X = X[:, permutation]
shuffled_Y = Y[:, permutation].reshape((Y.shape[0],m))
# Step 2: Partition (shuffled_X, shuffled_Y). Minus the end case.
num_complete_minibatches = math.floor(m/mini_batch_size) # number of mini batches of size mini_batch_size in your partitionning
for k in range(0, num_complete_minibatches):
mini_batch_X = shuffled_X[:, k * mini_batch_size : k * mini_batch_size + mini_batch_size]
mini_batch_Y = shuffled_Y[:, k * mini_batch_size : k * mini_batch_size + mini_batch_size]
mini_batch = (mini_batch_X, mini_batch_Y)
mini_batches.append(mini_batch)
# Handling the end case (last mini-batch < mini_batch_size)
if m % mini_batch_size != 0:
mini_batch_X = shuffled_X[:, num_complete_minibatches * mini_batch_size : m]
mini_batch_Y = shuffled_Y[:, num_complete_minibatches * mini_batch_size : m]
mini_batch = (mini_batch_X, mini_batch_Y)
mini_batches.append(mini_batch)
return mini_batches
def convert_to_one_hot(Y, C):
Y = np.eye(C)[Y.reshape(-1)].T
return Y
def predict(X, parameters):
W1 = tf.convert_to_tensor(parameters["W1"])
b1 = tf.convert_to_tensor(parameters["b1"])
W2 = tf.convert_to_tensor(parameters["W2"])
b2 = tf.convert_to_tensor(parameters["b2"])
W3 = tf.convert_to_tensor(parameters["W3"])
b3 = tf.convert_to_tensor(parameters["b3"])
params = {"W1": W1,
"b1": b1,
"W2": W2,
"b2": b2,
"W3": W3,
"b3": b3}
x = tf.placeholder("float", [12288, 1]) #这里是预测，即只输入一张图片进去预测其类别，所以样本数为‘1’
z3 = forward_propagation_for_predict(x, params)
p = tf.argmax(z3)
sess = tf.Session()
prediction = sess.run(p, feed_dict = {x: X})
return prediction
def forward_propagation_for_predict(X, parameters):
# Retrieve the parameters from the dictionary "parameters"
W1 = parameters['W1']
b1 = parameters['b1']
W2 = parameters['W2']
b2 = parameters['b2']
W3 = parameters['W3']
b3 = parameters['b3']
# Numpy Equivalents:
Z1 = tf.add(tf.matmul(W1, X), b1) # Z1 = np.dot(W1, X) + b1
A1 = tf.nn.relu(Z1) # A1 = relu(Z1)
Z2 = tf.add(tf.matmul(W2, A1), b2) # Z2 = np.dot(W2, a1) + b2
A2 = tf.nn.relu(Z2) # A2 = relu(Z2)
Z3 = tf.add(tf.matmul(W3, A2), b3) # Z3 = np.dot(W3,Z2) + b3
return Z3
predict.py---载入模型进行预测
import numpy as np
import matplotlib.pyplot as plt
import tensorflow as tf
from tensorflow.python.framework import ops
import scipy
from PIL import Image
from scipy import ndimage
import tensorflow_tutorial
# 载入待预测的图片
my_image = "thumbs_up.jpg"
fname = "images/" + my_image
# 将图片转换成我们训练的神经网络输入的格式
image = np.array(ndimage.imread(fname, flatten=False))
my_image = scipy.misc.imresize(image, size=(64,64)).reshape((1, 64*64*3)).T
with tf.Graph().as_default() as g:
# 给送入训练好的神经网络进行预测的图片数据占位
x = tf.placeholder(tf.float32, shape=(12288,None))
#初始化神经网络变量
parameters=tensorflow_tutorial.initialize_parameters()
#建立计算图（前向传播）
Z3=tensorflow_tutorial.forward_propagation(x,parameters)
# 预测图片类别
p=tf.argmax(Z3)
# 实例化 saver 对象
saver = tf.train.Saver()
with tf.Session() as sess:
# 将加载指定路径下的ckpt，若模型存在，则加载模型到当前对话
ckpt = tf.train.get_checkpoint_state('./model')
saver.restore(sess, ckpt.model_checkpoint_path)
# 进行预测
prediction=sess.run(p,feed_dict={x:my_image})
print(prediction）# 打印出预测结果
网友评论