Tags: Programming MachineLearning
[TOC]
03_linreg_starter.py
报错：
(Can not convert a float32 into a Tensor or Operation.)
在求loss的时候接收参数和run里面的参数一样，将接收参数修改避免冲突。
将：
_, loss = sess.run([optimizer,loss], feed_dict={X:x, Y:y})
改为：
_, l = sess.run([optimizer,loss], feed_dict={X:x, Y:y})
""" Starter code for simple linear regression example using placeholders
Created by Chip Huyen (huyenn@cs.stanford.edu)
CS20: "TensorFlow for Deep Learning Research"
cs20.stanford.edu
Lecture 03
"""
import os
os.environ['TF_CPP_MIN_LOG_LEVEL']='2'
import time
import numpy as np
import matplotlib.pyplot as plt
import tensorflow as tf
import utils
DATA_FILE = 'data/birth_life_2010.txt'
# Step 1: read in data from the .txt file
data, n_samples = utils.read_birth_life_data(DATA_FILE)
# Step 2: create placeholders for X (birth rate) and Y (life expectancy)
# Remember both X and Y are scalars with type float
X, Y = None, None
#############################
########## TO DO ############
#############################
X = tf.placeholder(dtype = tf.float32, name = "X")
Y = tf.placeholder(dtype = tf.float32, name = "Y") # [] means for scalar
# Step 3: create weight and bias, initialized to 0.0
# Make sure to use tf.get_variable
w, b = None, None
#############################
########## TO DO ############
#############################
w = tf.get_variable(name = "weights", initializer = tf.constant(0.0))
b = tf.get_variable(name = "bias", initializer = tf.constant(0.0))
# Step 4: build model to predict Y
# e.g. how would you derive at Y_predicted given X, w, and b
Y_predicted = None
#############################
########## TO DO ############
#############################
Y_predict = tf.add(tf.multiply(X,w),b)
# Step 5: use the square error as the loss function
loss = None
#############################
########## TO DO ############
#############################
loss = tf.square(tf.subtract(Y_predict, Y), name='loss')
# Step 6: using gradient descent with learning rate of 0.001 to minimize loss
optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.001).minimize(loss)
start = time.time()
# Create a filewriter to write the model's graph to TensorBoard
#############################
########## TO DO ############
#############################
writer = tf.summary.FileWriter('./graphs/linear_reg', tf.get_default_graph())
with tf.Session() as sess:
# Step 7: initialize the necessary variables, in this case, w and b
#############################
########## TO DO ############
#############################
sess.run(tf.global_variables_initializer())
# Step 8: train the model for 100 epochs
for i in range(100):
total_loss = 0
for x, y in data:
# Execute train_op and get the value of loss.
# Don't forget to feed in data for placeholders
_, l = sess.run([optimizer,loss], feed_dict={X:x, Y:y})
total_loss += l
print('Epoch {0}: {1}'.format(i, total_loss/n_samples))
# close the writer when you're done using it
#############################
########## TO DO ############
#############################
writer.close()
# Step 9: output the values of w and b
w_out, b_out = None, None
#############################
########## TO DO ############
#############################
w_out, b_out = sess.run([w, b])
print('Took: %f seconds' %(time.time() - start))
# uncomment the following lines to see the plot
plt.plot(data[:,0], data[:,1], 'bo', label='Real data')
plt.plot(data[:,0], data[:,0] * w_out + b_out, 'r', label='Predicted data')
plt.legend()
plt.show()
03_logreg_starter.py
改进1：改用exponential_decay, 92.75% 验证准确度。
""" Starter code for simple logistic regression model for MNIST
with tf.data module
MNIST dataset: yann.lecun.com/exdb/mnist/
Created by Chip Huyen (chiphuyen@cs.stanford.edu)
CS20: "TensorFlow for Deep Learning Research"
cs20.stanford.edu
Lecture 03
"""
import os
os.environ['TF_CPP_MIN_LOG_LEVEL']='2'
import numpy as np
import tensorflow as tf
import time
import utils
# Define paramaters for the model
learning_rate = 0.01
batch_size = 128
n_epochs = 30
n_train = 60000
n_test = 10000
# Step 1: Read in data
mnist_folder = 'data/mnist'
utils.download_mnist(mnist_folder)
train, val, test = utils.read_mnist(mnist_folder, flatten=True)
print(type(train))
# Step 2: Create datasets and iterator
# create training Dataset and batch it
train_data = tf.data.Dataset.from_tensor_slices(train)
train_data = train_data.shuffle(10000) # if you want to shuffle your data
train_data = train_data.batch(batch_size)
# create testing Dataset and batch it
test_data = tf.data.Dataset.from_tensor_slices(test)
test_data = test_data.shuffle(10000)
test_data = test_data.batch(10000)
# create one iterator and initialize it with different datasets
iterator = tf.data.Iterator.from_structure(train_data.output_types,
train_data.output_shapes)
img, label = iterator.get_next()
print(img.shape)
print(label.shape)
train_init = iterator.make_initializer(train_data) # initializer for train_data
test_init = iterator.make_initializer(test_data) # initializer for train_data
# Step 3: create weights and bias
# w is initialized to random variables with mean of 0, stddev of 0.01
# b is initialized to 0
# shape of w depends on the dimension of X and Y so that Y = tf.matmul(X, w)
# shape of b depends on Y
w, b = None, None
#############################
########## TO DO ############
#############################
w = tf.get_variable(initializer = tf.random_normal_initializer(mean=0, stddev=0.01), shape = [784,10], name = "weights")
b = tf.get_variable(initializer = tf.random_normal_initializer(mean=0, stddev=0.01), shape = [1,10], name = "bias")
# Step 4: build model
# the model that returns the logits.
# this logits will be later passed through softmax layer
logits = None
#############################
########## TO DO ############
#############################
logits = tf.matmul(img, w) + b
# Step 5: define loss function
# use cross entropy of softmax of logits as the loss function
loss = None
#############################
########## TO DO ############
#############################
entropy = tf.nn.softmax_cross_entropy_with_logits(labels = label, logits=logits, name="entropy")
loss = tf.reduce_mean(entropy, name = "loss")
# Step 6: define optimizer
# using Adamn Optimizer with pre-defined learning rate to minimize loss
optimizer = None
#############################
########## TO DO ############
#############################
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(loss)
# Step 7: calculate accuracy with test set
preds = tf.nn.softmax(logits)
correct_preds = tf.equal(tf.argmax(preds, 1), tf.argmax(label, 1))
accuracy = tf.reduce_sum(tf.cast(correct_preds, tf.float32))
writer = tf.summary.FileWriter('./graphs/logreg', tf.get_default_graph())
with tf.Session() as sess:
start_time = time.time()
sess.run(tf.global_variables_initializer())
# train the model n_epochs times
for i in range(n_epochs):
sess.run(train_init) # drawing samples from train_data
total_loss = 0
n_batches = 0
try:
while True:
_, l = sess.run([optimizer, loss])
total_loss += l
n_batches += 1
except tf.errors.OutOfRangeError:
pass
print('Average loss epoch {0}: {1}'.format(i, total_loss/n_batches))
print('Total time: {0} seconds'.format(time.time() - start_time))
# test the model
sess.run(test_init) # drawing samples from test_data
total_correct_preds = 0
try:
while True:
accuracy_batch = sess.run(accuracy)
total_correct_preds += accuracy_batch
except tf.errors.OutOfRangeError:
pass
print('Accuracy {0}'.format(total_correct_preds/n_test))
writer.close()
q2b.py
修改学习率和迭代次数：0.8876
""" Starter code for simple logistic regression model for MNIST
with tf.data module
MNIST dataset: yann.lecun.com/exdb/mnist/
Created by Chip Huyen (chiphuyen@cs.stanford.edu)
CS20: "TensorFlow for Deep Learning Research"
cs20.stanford.edu
Lecture 03
"""
import os
os.environ['TF_CPP_MIN_LOG_LEVEL']='2'
import numpy as np
import tensorflow as tf
import time
import utils
# Define paramaters for the model
global_step = tf.Variable(0, trainable=False)
learning_rate = 0.001
# learning_rate = tf.train.exponential_decay(0.01, global_step, decay_steps = 10, decay_rate = 0.2)
batch_size = 128
n_epochs = 100
n_train = 60000
n_test = 10000
# Step 1: Read in data
mnist_folder = 'data/notMNIST_large'
# utils.download_mnist(mnist_folder)
train, val, test = utils.read_mnist(mnist_folder, flatten=True)
# print(type(train))
# Step 2: Create datasets and iterator
# create training Dataset and batch it
train_data = tf.data.Dataset.from_tensor_slices(train)
train_data = train_data.shuffle(10000) # if you want to shuffle your data
train_data = train_data.batch(batch_size)
# create testing Dataset and batch it
test_data = tf.data.Dataset.from_tensor_slices(test)
test_data = test_data.shuffle(10000)
test_data = test_data.batch(10000)
# create one iterator and initialize it with different datasets
iterator = tf.data.Iterator.from_structure(train_data.output_types,
train_data.output_shapes)
img, label = iterator.get_next()
# print(img.shape)
# print(label.shape)
train_init = iterator.make_initializer(train_data) # initializer for train_data
test_init = iterator.make_initializer(test_data) # initializer for train_data
# Step 3: create weights and bias
# w is initialized to random variables with mean of 0, stddev of 0.01
# b is initialized to 0
# shape of w depends on the dimension of X and Y so that Y = tf.matmul(X, w)
# shape of b depends on Y
w, b = None, None
#############################
########## TO DO ############
#############################
w = tf.get_variable(initializer = tf.random_normal_initializer(mean=0, stddev=0.01), shape = [784,10], name = "weights")
b = tf.get_variable(initializer = tf.random_normal_initializer(mean=0, stddev=0.01), shape = [1,10], name = "bias")
# Step 4: build model
# the model that returns the logits.
# this logits will be later passed through softmax layer
logits = None
#############################
########## TO DO ############
#############################
logits = tf.matmul(img, w) + b
# Step 5: define loss function
# use cross entropy of softmax of logits as the loss function
loss = None
#############################
########## TO DO ############
#############################
entropy = tf.nn.softmax_cross_entropy_with_logits(labels = label, logits=logits, name="entropy")
loss = tf.reduce_mean(entropy, name = "loss")
# Step 6: define optimizer
# using Adamn Optimizer with pre-defined learning rate to minimize loss
optimizer = None
#############################
########## TO DO ############
#############################
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(loss, global_step=global_step)
# Step 7: calculate accuracy with test set
preds = tf.nn.softmax(logits)
correct_preds = tf.equal(tf.argmax(preds, 1), tf.argmax(label, 1))
accuracy = tf.reduce_sum(tf.cast(correct_preds, tf.float32))
writer = tf.summary.FileWriter('./graphs/logreg_notMNIST', tf.get_default_graph())
with tf.Session() as sess:
start_time = time.time()
sess.run(tf.global_variables_initializer())
# train the model n_epochs times
for i in range(n_epochs):
sess.run(train_init) # drawing samples from train_data
total_loss = 0
n_batches = 0
#if i % 10 == 0:
# learning_rate *= 0.2
# optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(loss)
try:
while True:
_, l = sess.run([optimizer, loss])
total_loss += l
n_batches += 1
except tf.errors.OutOfRangeError:
pass
print('Average loss epoch {0}: {1}'.format(i, total_loss/n_batches))
print('Total time: {0} seconds'.format(time.time() - start_time))
# test the model
sess.run(test_init) # drawing samples from test_data
total_correct_preds = 0
try:
while True:
accuracy_batch = sess.run(accuracy)
total_correct_preds += accuracy_batch
except tf.errors.OutOfRangeError:
pass
print('Accuracy {0}'.format(total_correct_preds/n_test))
writer.close()
网友评论