Tensorflow之迁移学习_Transfer Learning by 何子辰

>>> 通过mofanPython进行学习之后，自己测试了一下迁移学习；

>>> 这个是一个使用VGG16的简单迁移学习，在后面将进行微调将VGG的分类任务用来做回归；

>>>回归目标：用来预测老虎和猫的长度；

>>>伪造了长度信息：

　　... 猫：正态分布(40,8) #平均40cm, 方差为8

　　... 虎：正态分布(100,30) #平均100cm，方差为30

>>>VGG的模型和参数来自于Git：

　　https://github.com/machrisaa/tensorflow-vgg

>>>导入工具包：

1 from urllib.request import urlretrieve
2 import os
3 import numpy as np
4 import tensorflow as tf
5 import skimage.io
6 import skimage.transform
7 import cv2
8 import matplotlib.pyplot as plt

>>>构建数据集第一步：下载图片

def download():     # download tiger and kittycat image
    categories = ['tiger', 'kittycat']
    for category in categories:
        os.makedirs('./for_transfer_learning/data/%s' % category, exist_ok=True)
        with open('./for_transfer_learning/imagenet_%s.txt' % category, 'r') as file:
            urls = file.readlines()
            n_urls = len(urls)
            for i, url in enumerate(urls):
                try:
                    urlretrieve(url.strip(), './for_transfer_learning/data/%s/%s' % (category, url.strip().split('/')[-1]))
                    print('%s %i/%i' % (category, i, n_urls))
                except:
                    print('%s %i/%i' % (category, i, n_urls), 'no image')

>>>读取图片并进行resize操作

def load_data():
    imgs = {'tiger': [], 'kittycat': []}
    for k in imgs.keys():
        dir = './for_transfer_learning/data/' + k
        for file in os.listdir(dir):
            if not file.lower().endswith('.jpg'):
                continue
            try:
                resized_img = load_img(os.path.join(dir, file))
            except OSError:
                continue
            imgs[k].append(resized_img)    # [1, height, width, depth] * n
            if len(imgs[k]) == 400:        # only use 400 imgs to reduce my memory load
                break
    # fake length data for tiger and cat
    tigers_y = np.maximum(20, np.random.randn(len(imgs['tiger']), 1) * 30 + 100)
    cat_y = np.maximum(10, np.random.randn(len(imgs['kittycat']), 1) * 8 + 40)
    return imgs['tiger'], imgs['kittycat'], tigers_y, cat_y

>>>微调VGG，只对后面的全连接层进行训练

class Vgg16:
    vgg_mean = [103.939, 116.779, 123.68]

    def __init__(self, vgg16_npy_path=None, restore_from=None):
        # pre-trained parameters
        try:
            self.data_dict = np.load(vgg16_npy_path, encoding='latin1').item()
        except FileNotFoundError:
            print('Please download VGG16 parameters from here https://mega.nz/#!YU1FWJrA!O1ywiCS2IiOlUCtCpI6HTJOMrneN-Qdv3ywQP5poecM\nOr from my Baidu Cloud: https://pan.baidu.com/s/1Spps1Wy0bvrQHH2IMkRfpg')

        self.tfx = tf.placeholder(tf.float32, [None, 224, 224, 3])
        self.tfy = tf.placeholder(tf.float32, [None, 1])

        # Convert RGB to BGR
        red, green, blue = tf.split(axis=3, num_or_size_splits=3, value=self.tfx * 255.0)
        bgr = tf.concat(axis=3, values=[
            blue - self.vgg_mean[0],
            green - self.vgg_mean[1],
            red - self.vgg_mean[2],
        ])

        # pre-trained VGG layers are fixed in fine-tune
        conv1_1 = self.conv_layer(bgr, "conv1_1")
        conv1_2 = self.conv_layer(conv1_1, "conv1_2")
        pool1 = self.max_pool(conv1_2, 'pool1')

        conv2_1 = self.conv_layer(pool1, "conv2_1")
        conv2_2 = self.conv_layer(conv2_1, "conv2_2")
        pool2 = self.max_pool(conv2_2, 'pool2')

        conv3_1 = self.conv_layer(pool2, "conv3_1")
        conv3_2 = self.conv_layer(conv3_1, "conv3_2")
        conv3_3 = self.conv_layer(conv3_2, "conv3_3")
        pool3 = self.max_pool(conv3_3, 'pool3')

        conv4_1 = self.conv_layer(pool3, "conv4_1")
        conv4_2 = self.conv_layer(conv4_1, "conv4_2")
        conv4_3 = self.conv_layer(conv4_2, "conv4_3")
        pool4 = self.max_pool(conv4_3, 'pool4')

        conv5_1 = self.conv_layer(pool4, "conv5_1")
        conv5_2 = self.conv_layer(conv5_1, "conv5_2")
        conv5_3 = self.conv_layer(conv5_2, "conv5_3")
        pool5 = self.max_pool(conv5_3, 'pool5')

        # detach original VGG fc layers and
        # reconstruct your own fc layers serve for your own purpose
        self.flatten = tf.reshape(pool5, [-1, 7*7*512])
        self.fc6 = tf.layers.dense(self.flatten, 256, tf.nn.relu, name='fc6')
        self.out = tf.layers.dense(self.fc6, 1, name='out')

        self.sess = tf.Session()
        if restore_from:
            saver = tf.train.Saver()
            saver.restore(self.sess, restore_from)
        else:   # training graph
            self.loss = tf.losses.mean_squared_error(labels=self.tfy, predictions=self.out)
            self.train_op = tf.train.RMSPropOptimizer(0.001).minimize(self.loss)
            self.sess.run(tf.global_variables_initializer())

    def max_pool(self, bottom, name):
        return tf.nn.max_pool(bottom, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME', name=name)

    def conv_layer(self, bottom, name):
        with tf.variable_scope(name):   # CNN's filter is constant, NOT Variable that can be trained
            conv = tf.nn.conv2d(bottom, self.data_dict[name][0], [1, 1, 1, 1], padding='SAME')
            lout = tf.nn.relu(tf.nn.bias_add(conv, self.data_dict[name][1]))
            return lout

    def train(self, x, y):
        loss, _ = self.sess.run([self.loss, self.train_op], {self.tfx: x, self.tfy: y})
        return loss

    def predict(self, paths):
        fig, axs = plt.subplots(1, 2)
        for i, path in enumerate(paths):
            x = load_img(path)
            length = self.sess.run(self.out, {self.tfx: x})
            axs[i].imshow(x[0])
            axs[i].set_title('Len: %.1f cm' % length)
            axs[i].set_xticks(()); axs[i].set_yticks(())
        plt.show()

    def save(self, path='./for_transfer_learning/model/transfer_learn'):
        saver = tf.train.Saver()
        saver.save(self.sess, path, write_meta_graph=False)

>>>进行训练，输出Loss, epoch为100, batchsize为6

def train():
    tigers_x, cats_x, tigers_y, cats_y = load_data()

    # plot fake length distribution
    plt.hist(tigers_y, bins=20, label='Tigers')
    plt.hist(cats_y, bins=10, label='Cats')
    plt.legend()
    plt.xlabel('length')
    plt.show()

    xs = np.concatenate(tigers_x + cats_x, axis=0)
    ys = np.concatenate((tigers_y, cats_y), axis=0)

    vgg = Vgg16(vgg16_npy_path='./for_transfer_learning/vgg16.npy')
    print('Net built')
    for i in range(100):
        b_idx = np.random.randint(0, len(xs), 6)
        train_loss = vgg.train(xs[b_idx], ys[b_idx])
        print(i, 'train loss: ', train_loss)

    vgg.save('./for_transfer_learning/model/transfer_learn')      # save learned fc layers

>>>进行预测

def eval():
    vgg = Vgg16(vgg16_npy_path='./for_transfer_learning/vgg16.npy',
                restore_from='./for_transfer_learning/model/transfer_learn')
    vgg.predict(
        ['./for_transfer_learning/data/kittycat/000129037.jpg', './for_transfer_learning/data/tiger/391412.jpg'])


if __name__ == '__main__':
    # download()
    # train()
    eval()

 

转载于:https://www.cnblogs.com/IrivingLoveLuna/p/10340789.html