目录
使用TF-Slim进行基于17flowers数据集的分类器训练
环境测试
运行以下命令,以确认tf.contrib.slim模块安装已安装正确。
python -c "import tensorflow.contrib.slim as slim; eval = slim.evaluation.evaluate_once"
模块导入
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import matplotlib
%matplotlib inline
import matplotlib.pyplot as plt
import math
import numpy as np
import tensorflow as tf
import time
from datasets import dataset_utils
# Main slim library
from tensorflow.contrib import slim
使用TF-Slim创建一个多层感知器
def regression_model(inputs, is_training=True, scope="deep_regression"):
"""Creates the regression model.
参数值:
inputs: A node that yields a `Tensor` of size [batch_size, dimensions].
is_training: Whether or not we're currently training the model.
scope: An optional variable_op scope for the model.
返回值:
predictions: 1-D `Tensor` of shape [batch_size] of responses.
end_points: A dict of end points representing the hidden layers.
"""
with tf.variable_scope(scope, 'deep_regression', [inputs]):
end_points = {}
# 使用slim.arg_scope为slim.fully_connected设置默认的参数:weight _regularizer和acvitation
with slim.arg_scope([slim.fully_connected],
activation_fn=tf.nn.relu,
weights_regularizer=slim.l2_regularizer(0.01)):
# 创建一个包含32个隐藏节点的全连接层,end_points这个字典用于将隐藏层单元返回
net = slim.fully_connected(inputs, 32, scope='fc1')
end_points['fc1'] = net
# 添加dropout层来防止过拟合
net = slim.dropout(net, 0.8, is_training=is_training)
# 创建一个包含16个隐藏节点的全连接层
net = slim.fully_connected(net, 16, scope='fc2')
end_points['fc2'] = net
# 创建包含1个隐藏节点的隐藏层。设置激活函数为空使得线性化
predictions = slim.fully_connected(net, 1, activation_fn=None, scope='prediction')
end_points['out'] = predictions
return predictions, end_points
打印变量名
with tf.Graph().as_default():
# Dummy placeholders for arbitrary number of 1d inputs and outputs
inputs = tf.placeholder(tf.float32, shape=(None, 1))
outputs = tf.placeholder(tf.float32, shape=(None, 1))
# Build model
predictions, end_points = regression_model(inputs)
# Print name and shape of each tensor.
print("Layers")
for k, v in end_points.items():
print('name = {}, shape = {}'.format(v.name, v.get_shape()))
# Print name and shape of parameter nodes (values not yet initialized)
print("\n")
print("Parameters")
for v in slim.get_model_variables():
print('name = {}, shape = {}'.format(v.name, v.get_shape()))
产生批量训练数据
def produce_batch(batch_size, noise=0.3):
xs = np.random.random(size=[batch_size, 1]) * 10
ys = np.sin(xs) + 5 + np.random.normal(size=[batch_size, 1], scale=noise)
return [xs.astype(np.float32), ys.astype(np.float32)]
x_train, y_train = produce_batch(200)
x_test, y_test = produce_batch(200)
plt.scatter(x_train, y_train)
定义张量生成函数
def convert_data_to_tensors(x, y):
inputs = tf.constant(x)
inputs.set_shape([None, 1])
outputs = tf.constant(y)
outputs.set_shape([None, 1])
return inputs, outputs
创建模型并训练
# The following snippet trains the regression model using a mean_squared_error loss.
ckpt_dir = '/tmp/regression_model/'
with tf.Graph().as_default():
tf.logging.set_verbosity(tf.logging.INFO)
inputs, targets = convert_data_to_tensors(x_train, y_train)
# Make the model.
predictions, nodes = regression_model(inputs, is_training=True)
# Add the loss function to the graph.
loss = tf.losses.mean_squared_error(labels=targets, predictions=predictions)
# The total loss is the user's loss plus any regularization losses.
total_loss = slim.losses.get_total_loss()
# Specify the optimizer and create the train op:
optimizer = tf.train.AdamOptimizer(learning_rate=0.005)
train_op = slim.learning.create_train_op(total_loss, optimizer)
# Run the training inside a session.
final_loss = slim.learning.train(
train_op,
logdir=ckpt_dir,
number_of_steps=5000,
save_summaries_secs=5,
log_every_n_steps=500)
print("Finished training. Last batch loss:", final_loss)
print("Checkpoint saved in %s" % ckpt_dir)
添加多种损失函数
with tf.Graph().as_default():
inputs, targets = convert_data_to_tensors(x_train, y_train)
predictions, end_points = regression_model(inputs, is_training=True)
# Add multiple loss nodes.
mean_squared_error_loss = tf.losses.mean_squared_error(labels=targets, predictions=predictions)
absolute_difference_loss = slim.losses.absolute_difference(predictions, targets)
# The following two ways to compute the total loss are equivalent
regularization_loss = tf.add_n(slim.losses.get_regularization_losses())
total_loss1 = mean_squared_error_loss + absolute_difference_loss + regularization_loss
# Regularization Loss is included in the total loss by default.
# This is good for training, but not for testing.
total_loss2 = slim.losses.get_total_loss(add_regularization_losses=True)
init_op = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init_op) # Will initialize the parameters with random weights.
total_loss1, total_loss2 = sess.run([total_loss1, total_loss2])
print('Total Loss1: %f' % total_loss1)
print('Total Loss2: %f' % total_loss2)
print('Regularization Losses:')
for loss in slim.losses.get_regularization_losses():
print(loss)
print('Loss Functions:')
for loss in slim.losses.get_losses():
print(loss)
导入模型并进行预测
with tf.Graph().as_default():
inputs, targets = convert_data_to_tensors(x_test, y_test)
# Create the model structure. (Parameters will be loaded below.)
predictions, end_points = regression_model(inputs, is_training=False)
# Make a session which restores the old parameters from a checkpoint.
sv = tf.train.Supervisor(logdir=ckpt_dir)
with sv.managed_session() as sess:
inputs, predictions, targets = sess.run([inputs, predictions, targets])
plt.scatter(inputs, targets, c='r');
plt.scatter(inputs, predictions, c='b');
plt.title('red=true, blue=predicted')
进行模型评估
with tf.Graph().as_default():
inputs, targets = convert_data_to_tensors(x_test, y_test)
predictions, end_points = regression_model(inputs, is_training=False)
# Specify metrics to evaluate:
names_to_value_nodes, names_to_update_nodes = slim.metrics.aggregate_metric_map({
'Mean Squared Error': slim.metrics.streaming_mean_squared_error(predictions, targets),
'Mean Absolute Error': slim.metrics.streaming_mean_absolute_error(predictions, targets)
})
# Make a session which restores the old graph parameters, and then run eval.
sv = tf.train.Supervisor(logdir=ckpt_dir)
with sv.managed_session() as sess:
# metric_values = slim.evaluation.evaluation(sess,
# num_evals=1, # Single pass over data
# eval_op=names_to_update_nodes.values(),
# final_op=names_to_value_nodes.values())
metric_values = slim.evaluation.evaluation(sess, num_evals=1, eval_op=names_to_update_nodes.values(), final_op=names_to_value_nodes.values())
names_to_values = dict(zip(names_to_value_nodes.keys(), metric_values))
for key, value in names_to_values.items():
print('%s: %f' % (key, value))
使用TF-Slim进行基于17flowers数据集的分类器训练
下载数据集
import tensorflow as tf
from datasets import dataset_utils
url = "http://download.tensorflow.org/data/flowers.tar.gz"
flowers_data_dir = '/tmp/flowers'
if not tf.gfile.Exists(flowers_data_dir):
tf.gfile.MakeDirs(flowers_data_dir)
dataset_utils.download_and_uncompress_tarball(url, flowers_data_dir)
随机显示数据集中的图片
# from datasets import flowers
from datasets import cifar10
import tensorflow as tf
from tensorflow.contrib import slim
cifar10_data_dir = "./datasets/cifar10/tfrecords"
with tf.Graph().as_default():
# dataset = flowers.get_split('train', flowers_data_dir)
dataset = cifar10.get_split('train', cifar10_data_dir)
data_provider = slim.dataset_data_provider.DatasetDataProvider(
dataset, common_queue_capacity=32, common_queue_min=1)
image, label = data_provider.get(['image', 'label'])
with tf.Session() as sess:
with slim.queues.QueueRunners(sess):
for i in range(4):
np_image, np_label = sess.run([image, label])
height, width, _ = np_image.shape
class_name = name = dataset.labels_to_names[np_label]
plt.figure()
plt.imshow(np_image)
plt.title('%s, %d x %d' % (name, height, width))
plt.axis('off')
plt.show()
定义CNN网络
def my_cnn(images, num_classes, is_training): # is_training is not used...
with slim.arg_scope([slim.max_pool2d], kernel_size=[3, 3], stride=2):
net = slim.conv2d(images, 64, [5, 5])
net = slim.max_pool2d(net)
net = slim.conv2d(net, 64, [5, 5])
net = slim.max_pool2d(net)
net = slim.flatten(net)
net = slim.fully_connected(net, 192)
net = slim.fully_connected(net, num_classes, activation_fn=None)
return net
将模型应用到一些随机选取的图片
import tensorflow as tf
with tf.Graph().as_default():
# The model can handle any input size because the first layer is convolutional.
# The size of the model is determined when image_node is first passed into the my_cnn function.
# Once the variables are initialized, the size of all the weight matrices is fixed.
# Because of the fully connected layers, this means that all subsequent images must have the same
# input size as the first image.
batch_size, height, width, channels = 3, 28, 28, 3
images = tf.random_uniform([batch_size, height, width, channels], maxval=1)
# Create the model.
num_classes = 10
logits = my_cnn(images, num_classes, is_training=True)
probabilities = tf.nn.softmax(logits)
# Initialize all the variables (including parameters) randomly.
init_op = tf.global_variables_initializer()
with tf.Session() as sess:
# Run the init_op, evaluate the model outputs and print the results:
sess.run(init_op)
probabilities = sess.run(probabilities)
print('Probabilities Shape:')
print(probabilities.shape) # batch_size x num_classes
print('\nProbabilities:')
print(probabilities)
print('\nSumming across all classes (Should equal 1):')
print(np.sum(probabilities, 1)) # Each row sums to 1
使用创建的CNN网络进行训练
from preprocessing import inception_preprocessing
import tensorflow as tf
from tensorflow.contrib import slim
def load_batch(dataset, batch_size=32, height=32, width=32, is_training=False):
"""Loads a single batch of data.
Args:
dataset: The dataset to load.
batch_size: The number of images in the batch.
height: The size of each image after preprocessing.
width: The size of each image after preprocessing.
is_training: Whether or not we're currently training or evaluating.
Returns:
images: A Tensor of size [batch_size, height, width, 3], image samples that have been preprocessed.
images_raw: A Tensor of size [batch_size, height, width, 3], image samples that can be used for visualization.
labels: A Tensor of size [batch_size], whose values range between 0 and dataset.num_classes.
"""
data_provider = slim.dataset_data_provider.DatasetDataProvider(
dataset, common_queue_capacity=32,
common_queue_min=8)
image_raw, label = data_provider.get(['image', 'label'])
# Preprocess image for usage by Inception.
image = inception_preprocessing.preprocess_image(image_raw, height, width, is_training=is_training)
# Preprocess the image for display purposes.
image_raw = tf.expand_dims(image_raw, 0)
image_raw = tf.image.resize_images(image_raw, [height, width])
image_raw = tf.squeeze(image_raw)
# Batch it up.
images, images_raw, labels = tf.train.batch(
[image, image_raw, label],
batch_size=batch_size,
num_threads=1,
capacity=2 * batch_size)
return images, images_raw, labels
模型训练
from datasets import cifar10
# This might take a few minutes.
train_dir = './tfslim_model/'
cifar10_data_dir = "./datasets/cifar10/tfrecords"
print('Will save model to %s' % train_dir)
with tf.Graph().as_default():
tf.logging.set_verbosity(tf.logging.INFO)
dataset = cifar10.get_split('train', cifar10_data_dir)
images, _, labels = load_batch(dataset)
# Create the model:
logits = my_cnn(images, num_classes=dataset.num_classes, is_training=True)
# Specify the loss function:
one_hot_labels = slim.one_hot_encoding(labels, dataset.num_classes)
slim.losses.softmax_cross_entropy(logits, one_hot_labels)
total_loss = slim.losses.get_total_loss()
# Create some summaries to visualize the training process:
tf.summary.scalar('losses/Total Loss', total_loss)
# Specify the optimizer and create the train op:
optimizer = tf.train.AdamOptimizer(learning_rate=0.01)
train_op = slim.learning.create_train_op(total_loss, optimizer)
# Run the training:
final_loss = slim.learning.train(
train_op,
logdir=train_dir,
number_of_steps=100, # For speed, we just do 1 epoch
save_summaries_secs=1)
print('Finished training. Final batch loss %d' % final_loss)
模型评估
from datasets import cifar10
# This might take a few minutes.
with tf.Graph().as_default():
tf.logging.set_verbosity(tf.logging.DEBUG)
dataset = cifar10.get_split('train', cifar10_data_dir)
images, _, labels = load_batch(dataset)
logits = my_cnn(images, num_classes=dataset.num_classes, is_training=False)
predictions = tf.argmax(logits, 1)
# Define the metrics:
names_to_values, names_to_updates = slim.metrics.aggregate_metric_map({
'eval/Accuracy': slim.metrics.streaming_accuracy(predictions, labels),
'eval/Recall@5': slim.metrics.streaming_recall_at_k(logits, labels, 5),
})
print(names_to_values.values(), names_to_updates.values())
print('Running evaluation Loop...')
checkpoint_path = tf.train.latest_checkpoint(train_dir)
# metric_values = slim.evaluation.evaluate_once(
# master='',
# checkpoint_path=checkpoint_path,
# logdir=train_dir,
# eval_op=names_to_updates.values(),
# final_op=names_to_values.values())
# names_to_values = dict(zip(names_to_values.keys(), metric_values))
# for name in names_to_values:
# print('%s: %f' % (name, names_to_values[name]))
使用预训练模型
模型下载
from datasets import dataset_utils
url = "http://download.tensorflow.org/models/inception_v1_2016_08_28.tar.gz"
checkpoints_dir = '/tmp/checkpoints'
if not tf.gfile.Exists(checkpoints_dir):
tf.gfile.MakeDirs(checkpoints_dir)
dataset_utils.download_and_uncompress_tarball(url, checkpoints_dir)
使用模型进行预测
import numpy as np
import os
import tensorflow as tf
try:
import urllib2 as urllib
except ImportError:
import urllib.request as urllib
from datasets import imagenet
from nets import inception
from preprocessing import inception_preprocessing
from tensorflow.contrib import slim
image_size = inception.inception_v1.default_image_size
with tf.Graph().as_default():
url = 'https://upload.wikimedia.org/wikipedia/commons/7/70/EnglishCockerSpaniel_simon.jpg'
image_string = urllib.urlopen(url).read()
image = tf.image.decode_jpeg(image_string, channels=3)
processed_image = inception_preprocessing.preprocess_image(image, image_size, image_size, is_training=False)
processed_images = tf.expand_dims(processed_image, 0)
# Create the model, use the default arg scope to configure the batch norm parameters.
with slim.arg_scope(inception.inception_v1_arg_scope()):
logits, _ = inception.inception_v1(processed_images, num_classes=1001, is_training=False)
probabilities = tf.nn.softmax(logits)
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'inception_v1.ckpt'),
slim.get_model_variables('InceptionV1'))
with tf.Session() as sess:
init_fn(sess)
np_image, probabilities = sess.run([image, probabilities])
probabilities = probabilities[0, 0:]
sorted_inds = [i[0] for i in sorted(enumerate(-probabilities), key=lambda x:x[1])]
plt.figure()
plt.imshow(np_image.astype(np.uint8))
plt.axis('off')
plt.show()
names = imagenet.create_readable_names_for_imagenet_labels()
for i in range(5):
index = sorted_inds[i]
print('Probability %0.2f%% => [%s]' % (probabilities[index] * 100, names[index]))
使用VGG进行图片分类
VGG模型下载
from datasets import dataset_utils
import tensorflow as tf
url = "http://download.tensorflow.org/models/vgg_16_2016_08_28.tar.gz"
checkpoints_dir = '/tmp/checkpoints'
if not tf.gfile.Exists(checkpoints_dir):
tf.gfile.MakeDirs(checkpoints_dir)
dataset_utils.download_and_uncompress_tarball(url, checkpoints_dir)
使用预训练的VGG网络模型进行图片分类
import numpy as np
import os
import tensorflow as tf
try:
import urllib2
except ImportError:
import urllib.request as urllib
from datasets import imagenet
from nets import vgg
from preprocessing import vgg_preprocessing
from tensorflow.contrib import slim
image_size = vgg.vgg_16.default_image_size
with tf.Graph().as_default():
url = 'https://upload.wikimedia.org/wikipedia/commons/d/d9/First_Student_IC_school_bus_202076.jpg'
image_string = urllib.urlopen(url).read()
image = tf.image.decode_jpeg(image_string, channels=3)
processed_image = vgg_preprocessing.preprocess_image(image, image_size, image_size, is_training=False)
processed_images = tf.expand_dims(processed_image, 0)
# Create the model, use the default arg scope to configure the batch norm parameters.
with slim.arg_scope(vgg.vgg_arg_scope()):
# 1000 classes instead of 1001.
logits, _ = vgg.vgg_16(processed_images, num_classes=1000, is_training=False)
probabilities = tf.nn.softmax(logits)
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'vgg_16.ckpt'),
slim.get_model_variables('vgg_16'))
with tf.Session() as sess:
init_fn(sess)
np_image, probabilities = sess.run([image, probabilities])
probabilities = probabilities[0, 0:]
sorted_inds = [i[0] for i in sorted(enumerate(-probabilities), key=lambda x:x[1])]
plt.figure()
plt.imshow(np_image.astype(np.uint8))
plt.axis('off')
plt.show()
names = imagenet.create_readable_names_for_imagenet_labels()
for i in range(5):
index = sorted_inds[i]
# Shift the index of a class name by one.
print('Probability %0.2f%% => [%s]' % (probabilities[index] * 100, names[index+1]))
使用模型微调进行在数据集上进行训练
# Note that this may take several minutes.
import os
from datasets import flowers
from nets import inception
from preprocessing import inception_preprocessing
from tensorflow.contrib import slim
image_size = inception.inception_v1.default_image_size
def get_init_fn():
"""Returns a function run by the chief worker to warm-start the training."""
checkpoint_exclude_scopes=["InceptionV1/Logits", "InceptionV1/AuxLogits"]
exclusions = [scope.strip() for scope in checkpoint_exclude_scopes]
variables_to_restore = []
for var in slim.get_model_variables():
for exclusion in exclusions:
if var.op.name.startswith(exclusion):
break
else:
variables_to_restore.append(var)
return slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, 'inception_v1.ckpt'),
variables_to_restore)
train_dir = '/tmp/inception_finetuned/'
with tf.Graph().as_default():
tf.logging.set_verbosity(tf.logging.INFO)
dataset = flowers.get_split('train', flowers_data_dir)
images, _, labels = load_batch(dataset, height=image_size, width=image_size)
# Create the model, use the default arg scope to configure the batch norm parameters.
with slim.arg_scope(inception.inception_v1_arg_scope()):
logits, _ = inception.inception_v1(images, num_classes=dataset.num_classes, is_training=True)
# Specify the loss function:
one_hot_labels = slim.one_hot_encoding(labels, dataset.num_classes)
slim.losses.softmax_cross_entropy(logits, one_hot_labels)
total_loss = slim.losses.get_total_loss()
# Create some summaries to visualize the training process:
tf.summary.scalar('losses/Total Loss', total_loss)
# Specify the optimizer and create the train op:
optimizer = tf.train.AdamOptimizer(learning_rate=0.01)
train_op = slim.learning.create_train_op(total_loss, optimizer)
# Run the training:
final_loss = slim.learning.train(
train_op,
logdir=train_dir,
init_fn=get_init_fn(),
number_of_steps=2)
print('Finished training. Last batch loss %f' % final_loss)
使用微调后的模型进行图片分类
import numpy as np
import tensorflow as tf
from datasets import flowers
from nets import inception
from tensorflow.contrib import slim
image_size = inception.inception_v1.default_image_size
batch_size = 3
with tf.Graph().as_default():
tf.logging.set_verbosity(tf.logging.INFO)
dataset = flowers.get_split('train', flowers_data_dir)
images, images_raw, labels = load_batch(dataset, height=image_size, width=image_size)
# Create the model, use the default arg scope to configure the batch norm parameters.
with slim.arg_scope(inception.inception_v1_arg_scope()):
logits, _ = inception.inception_v1(images, num_classes=dataset.num_classes, is_training=True)
probabilities = tf.nn.softmax(logits)
checkpoint_path = tf.train.latest_checkpoint(train_dir)
init_fn = slim.assign_from_checkpoint_fn(
checkpoint_path,
slim.get_variables_to_restore())
with tf.Session() as sess:
with slim.queues.QueueRunners(sess):
sess.run(tf.initialize_local_variables())
init_fn(sess)
np_probabilities, np_images_raw, np_labels = sess.run([probabilities, images_raw, labels])
for i in range(batch_size):
image = np_images_raw[i, :, :, :]
true_label = np_labels[i]
predicted_label = np.argmax(np_probabilities[i, :])
predicted_name = dataset.labels_to_names[predicted_label]
true_name = dataset.labels_to_names[true_label]
plt.figure()
plt.imshow(image.astype(np.uint8))
plt.title('Ground Truth: [%s], Prediction [%s]' % (true_name, predicted_name))
plt.axis('off')
plt.show()