slim_walkthrough测试

最新推荐文章于 2022-03-10 20:19:40 发布

suiyuan2009

最新推荐文章于 2022-03-10 20:19:40 发布

阅读量220

点赞数

分类专栏： Tensorflow 文章标签： tensorflow 深度学习

本文链接：https://blog.csdn.net/suiyuan2009/article/details/105278986

版权

Tensorflow 专栏收录该内容

4 篇文章 0 订阅

订阅专栏

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()

suiyuan2009

关注

0
点赞
踩
1

收藏

觉得还不错? 一键收藏
0
评论
slim_walkthrough测试

目录目录目录环境测试模块导入使用TF-Slim创建一个多层感知器打印变量名产生批量训练数据定义张量生成函数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_on...
复制链接

扫一扫