【深度学习系列】用PaddlePaddle和Tensorflow实现经典CNN网络Vgg

 1 #coding:utf-8
 2 ‘‘‘
 3 Created by huxiaoman 2017.12.12
 4 vggnet.py:用vgg网络实现cifar-10分类
 5 ‘‘‘
 6 
 7 import paddle.v2 as paddle
 8 
 9 def vgg(input):
10     def conv_block(ipt, num_filter, groups, dropouts, num_channels=None):
11         return paddle.networks.img_conv_group(
12             input=ipt,
13             num_channels=num_channels,
14             pool_size=2,
15             pool_stride=2,
16             conv_num_filter=[num_filter] * groups,
17             conv_filter_size=3,
18             conv_act=paddle.activation.Relu(),
19             conv_with_batchnorm=True,
20             conv_batchnorm_drop_rate=dropouts,
21             pool_type=paddle.pooling.Max())
22 
23     conv1 = conv_block(input, 64, 2, [0.3, 0], 3)
24     conv2 = conv_block(conv1, 128, 2, [0.4, 0])
25     conv3 = conv_block(conv2, 256, 3, [0.4, 0.4, 0])
26     conv4 = conv_block(conv3, 512, 3, [0.4, 0.4, 0])
27     conv5 = conv_block(conv4, 512, 3, [0.4, 0.4, 0])
28 
29     drop = paddle.layer.dropout(input=conv5, dropout_rate=0.5)
30     fc1 = paddle.layer.fc(input=drop, size=512, act=paddle.activation.Linear())
31     bn = paddle.layer.batch_norm(
32         input=fc1,
33         act=paddle.activation.Relu(),
34         layer_attr=paddle.attr.Extra(drop_rate=0.5))
35     fc2 = paddle.layer.fc(input=bn, size=512, act=paddle.activation.Linear())
36     return fc2

  1 #coding:utf-8
  2 ‘‘‘
  3 Created by huxiaoman 2017.12.12
  4 train_vgg.py:训练vgg16对cifar10数据集进行分类
  5 ‘‘‘
  6 
  7 import sys, os
  8 import paddle.v2 as paddle
  9 from vggnet import vgg
 10 
 11 with_gpu = os.getenv(‘WITH_GPU‘, ‘0‘) != ‘1‘
 12 
 13 def main():
 14     datadim = 3 * 32 * 32
 15     classdim = 10
 16 
 17     # PaddlePaddle init
 18     paddle.init(use_gpu=with_gpu, trainer_count=8)
 19 
 20     image = paddle.layer.data(
 21         name="image", type=paddle.data_type.dense_vector(datadim))
 22     
 23     net = vgg(image)
 24 
 25     out = paddle.layer.fc(
 26         input=net, size=classdim, act=paddle.activation.Softmax())
 27 
 28     lbl = paddle.layer.data(
 29         name="label", type=paddle.data_type.integer_value(classdim))
 30     cost = paddle.layer.classification_cost(input=out, label=lbl)
 31 
 32     # Create parameters
 33     parameters = paddle.parameters.create(cost)
 34 
 35     # Create optimizer
 36     momentum_optimizer = paddle.optimizer.Momentum(
 37         momentum=0.9,
 38         regularization=paddle.optimizer.L2Regularization(rate=0.0002 * 128),
 39         learning_rate=0.1 / 128.0,
 40         learning_rate_decay_a=0.1,
 41         learning_rate_decay_b=50000 * 100,
 42         learning_rate_schedule=‘discexp‘)
 43 
 44     # End batch and end pass event handler
 45     def event_handler(event):
 46         if isinstance(event, paddle.event.EndIteration):
 47             if event.batch_id % 100 == 0:
 48                 print "\nPass %d, Batch %d, Cost %f, %s" % (
 49                     event.pass_id, event.batch_id, event.cost, event.metrics)
 50             else:
 51                 sys.stdout.write(‘.‘)
 52                 sys.stdout.flush()
 53         if isinstance(event, paddle.event.EndPass):
 54             # save parameters
 55             with open(‘params_pass_%d.tar‘ % event.pass_id, ‘w‘) as f:
 56                 parameters.to_tar(f)
 57 
 58             result = trainer.test(
 59                 reader=paddle.batch(
 60                     paddle.dataset.cifar.test10(), batch_size=128),
 61                 feeding={‘image‘: 0,
 62                          ‘label‘: 1})
 63             print "\nTest with Pass %d, %s" % (event.pass_id, result.metrics)
 64 
 65     # Create trainer
 66     trainer = paddle.trainer.SGD(
 67         cost=cost, parameters=parameters, update_equation=momentum_optimizer)
 68 
 69     # Save the inference topology to protobuf.
 70     inference_topology = paddle.topology.Topology(layers=out)
 71     with open("inference_topology.pkl", ‘wb‘) as f:
 72         inference_topology.serialize_for_inference(f)
 73 
 74     trainer.train(
 75         reader=paddle.batch(
 76             paddle.reader.shuffle(
 77                 paddle.dataset.cifar.train10(), buf_size=50000),
 78             batch_size=128),
 79         num_passes=200,
 80         event_handler=event_handler,
 81         feeding={‘image‘: 0,
 82                  ‘label‘: 1})
 83 
 84     # inference
 85     from PIL import Image
 86     import numpy as np
 87     import os
 88 
 89     def load_image(file):
 90         im = Image.open(file)
 91         im = im.resize((32, 32), Image.ANTIALIAS)
 92         im = np.array(im).astype(np.float32)
 93         im = im.transpose((2, 0, 1))  # CHW
 94         im = im[(2, 1, 0), :, :]  # BGR
 95         im = im.flatten()
 96         im = im / 255.0
 97         return im
 98 
 99     test_data = []
100     cur_dir = os.path.dirname(os.path.realpath(__file__))
101     test_data.append((load_image(cur_dir + ‘/image/dog.png‘), ))
102 
103     probs = paddle.infer(
104         output_layer=out, parameters=parameters, input=test_data)
105     lab = np.argsort(-probs)  # probs and lab are the results of one batch data
106     print "Label of image/dog.png is: %d" % lab[0][0]
107 
108 
109 if __name__ == ‘__main__‘:
110     main()

 1 def inference_op(input_op, keep_prob):
 2     p = []
 3     # 第一块 conv1_1-conv1_2-pool1
 4     conv1_1 = conv_op(input_op, name=‘conv1_1‘, kh=3, kw=3,
 5                 n_out = 64, dh = 1, dw = 1, p = p)
 6     conv1_2 = conv_op(conv1_1, name=‘conv1_2‘, kh=3, kw=3,
 7                 n_out = 64, dh = 1, dw = 1, p = p)
 8     pool1 = mpool_op(conv1_2, name = ‘pool1‘, kh = 2, kw = 2,
 9                 dw = 2, dh = 2)
10     # 第二块 conv2_1-conv2_2-pool2
11     conv2_1 = conv_op(pool1, name=‘conv2_1‘, kh=3, kw=3,
12                 n_out = 128, dh = 1, dw = 1, p = p)
13     conv2_2 = conv_op(conv2_1, name=‘conv2_2‘, kh=3, kw=3,
14                 n_out = 128, dh = 1, dw = 1, p = p)
15     pool2 = mpool_op(conv2_2, name = ‘pool2‘, kh = 2, kw = 2,
16                 dw = 2, dh = 2)
17     # 第三块 conv3_1-conv3_2-conv3_3-pool3
18     conv3_1 = conv_op(pool2, name=‘conv3_1‘, kh=3, kw=3,
19                 n_out = 256, dh = 1, dw = 1, p = p)
20     conv3_2 = conv_op(conv3_1, name=‘conv3_2‘, kh=3, kw=3,
21                 n_out = 256, dh = 1, dw = 1, p = p)
22     conv3_3 = conv_op(conv3_2, name=‘conv3_3‘, kh=3, kw=3,
23                 n_out = 256, dh = 1, dw = 1, p = p)
24     pool3 = mpool_op(conv3_3, name = ‘pool3‘, kh = 2, kw = 2,
25                 dw = 2, dh = 2)
26     # 第四块 conv4_1-conv4_2-conv4_3-pool4
27     conv4_1 = conv_op(pool3, name=‘conv4_1‘, kh=3, kw=3,
28                 n_out = 512, dh = 1, dw = 1, p = p)
29     conv4_2 = conv_op(conv4_1, name=‘conv4_2‘, kh=3, kw=3,
30                 n_out = 512, dh = 1, dw = 1, p = p)
31     conv4_3 = conv_op(conv4_2, name=‘conv4_3‘, kh=3, kw=3,
32                 n_out = 512, dh = 1, dw = 1, p = p)
33     pool4 = mpool_op(conv4_3, name = ‘pool4‘, kh = 2, kw = 2,
34                 dw = 2, dh = 2)
35     # 第五块 conv5_1-conv5_2-conv5_3-pool5
36     conv5_1 = conv_op(pool4, name=‘conv5_1‘, kh=3, kw=3,
37                 n_out = 512, dh = 1, dw = 1, p = p)
38     conv5_2 = conv_op(conv5_1, name=‘conv5_2‘, kh=3, kw=3,
39                 n_out = 512, dh = 1, dw = 1, p = p)
40     conv5_3 = conv_op(conv5_2, name=‘conv5_3‘, kh=3, kw=3,
41                 n_out = 512, dh = 1, dw = 1, p = p)
42     pool5 = mpool_op(conv5_3, name = ‘pool5‘, kh = 2, kw = 2,
43                 dw = 2, dh = 2)
44     # 把pool5 ( [7, 7, 512] )  拉成向量
45     shp  = pool5.get_shape()
46     flattened_shape = shp[1].value * shp[2].value * shp[3].value
47     resh1 = tf.reshape(pool5, [-1, flattened_shape], name = ‘resh1‘)
48 
49     # 全连接层1 添加了 Droput来防止过拟合    
50     fc1 = fc_op(resh1, name = ‘fc1‘, n_out = 2048, p = p)
51     fc1_drop = tf.nn.dropout(fc1, keep_prob, name = ‘fc1_drop‘)
52 
53     # 全连接层2 添加了 Droput来防止过拟合    
54     fc2 = fc_op(fc1_drop, name = ‘fc2‘, n_out = 2048, p = p)
55     fc2_drop = tf.nn.dropout(fc2, keep_prob, name = ‘fc2_drop‘)
56 
57     # 全连接层3 加一个softmax求给类别的概率
58     fc3 = fc_op(fc2_drop, name = ‘fc3‘, n_out = 1000, p = p)
59     softmax = tf.nn.softmax(fc3)
60     predictions = tf.argmax(softmax, 1)
61     return predictions, softmax, fc3, p

  1 # -*- coding: utf-8 -*-
  2 """
  3 Created by huxiaoman 2017.12.12
  4 vgg_tf.py:训练tensorflow版的vgg16网络，对cifar-10shuju进行分类
  5 """
  6 from datetime import datetime
  7 import math
  8 import time
  9 import tensorflow as tf
 10 import cifar10
 11 
 12 batch_size = 128
 13 num_batches = 200
 14 
 15 # 定义函数对卷积层进行初始化
 16 # input_op : 输入数据 
 17 # name : 该卷积层的名字，用tf.name_scope()来命名
 18 # kh,kw : 分别是卷积核的高和宽
 19 # n_out : 输出通道数
 20 # dh,dw : 步长的高和宽
 21 # p ： 是参数列表，存储VGG所用到的参数
 22 # 采用xavier方法对卷积核权值进行初始化
 23 def conv_op(input_op, name, kh, kw, n_out, dh, dw, p):
 24     n_in = input_op.get_shape()[-1].value # 获得输入图像的通道数
 25     with tf.name_scope(name) as scope:
 26         kernel = tf.get_variable(scope+‘w‘,
 27             shape = [kh, kw, n_in, n_out], dtype = tf.float32,
 28             initializer = tf.contrib.layers.xavier_initializer_conv2d())
 29         #  卷积层计算
 30         conv = tf.nn.conv2d(input_op, kernel, (1, dh, dw, 1), padding = ‘SAME‘)
 31         bias_init_val = tf.constant(0.0, shape = [n_out], dtype = tf.float32)
 32         biases = tf.Variable(bias_init_val, trainable = True, name = ‘b‘)
 33         z = tf.nn.bias_add(conv, biases)
 34         activation = tf.nn.relu(z, name = scope)
 35         p += [kernel, biases]
 36         return activation
 37 
 38 # 定义函数对全连接层进行初始化
 39 # input_op : 输入数据
 40 # name : 该全连接层的名字
 41 # n_out : 输出的通道数
 42 # p : 参数列表 
 43 # 初始化方法用 xavier方法
 44 def fc_op(input_op, name, n_out, p):
 45     n_in = input_op.get_shape()[-1].value
 46 
 47     with tf.name_scope(name) as scope:
 48         kernel = tf.get_variable(scope+‘w‘,
 49             shape = [n_in, n_out], dtype = tf.float32,
 50             initializer = tf.contrib.layers.xavier_initializer())
 51         biases = tf.Variable(tf.constant(0.1, shape = [n_out],
 52             dtype = tf.float32), name = ‘b‘)
 53         activation = tf.nn.relu_layer(input_op, kernel,  #  ???????????????
 54             biases, name = scope)
 55         p += [kernel, biases]
 56         return activation 
 57 
 58 # 定义函数 创建 maxpool层
 59 # input_op : 输入数据 
 60 # name : 该卷积层的名字，用tf.name_scope()来命名
 61 # kh,kw : 分别是卷积核的高和宽
 62 # dh,dw : 步长的高和宽
 63 def mpool_op(input_op, name, kh, kw, dh, dw):
 64     return tf.nn.max_pool(input_op, ksize = [1,kh,kw,1],
 65         strides = [1, dh, dw, 1], padding = ‘SAME‘, name = name)
 66 
 67 #---------------创建 VGG-16------------------
 68 
 69 def inference_op(input_op, keep_prob):
 70     p = []
 71     # 第一块 conv1_1-conv1_2-pool1
 72     conv1_1 = conv_op(input_op, name=‘conv1_1‘, kh=3, kw=3,
 73                 n_out = 64, dh = 1, dw = 1, p = p)
 74     conv1_2 = conv_op(conv1_1, name=‘conv1_2‘, kh=3, kw=3,
 75                 n_out = 64, dh = 1, dw = 1, p = p)
 76     pool1 = mpool_op(conv1_2, name = ‘pool1‘, kh = 2, kw = 2,
 77                 dw = 2, dh = 2)
 78     # 第二块 conv2_1-conv2_2-pool2
 79     conv2_1 = conv_op(pool1, name=‘conv2_1‘, kh=3, kw=3,
 80                 n_out = 128, dh = 1, dw = 1, p = p)
 81     conv2_2 = conv_op(conv2_1, name=‘conv2_2‘, kh=3, kw=3,
 82                 n_out = 128, dh = 1, dw = 1, p = p)
 83     pool2 = mpool_op(conv2_2, name = ‘pool2‘, kh = 2, kw = 2,
 84                 dw = 2, dh = 2)
 85     # 第三块 conv3_1-conv3_2-conv3_3-pool3
 86     conv3_1 = conv_op(pool2, name=‘conv3_1‘, kh=3, kw=3,
 87                 n_out = 256, dh = 1, dw = 1, p = p)
 88     conv3_2 = conv_op(conv3_1, name=‘conv3_2‘, kh=3, kw=3,
 89                 n_out = 256, dh = 1, dw = 1, p = p)
 90     conv3_3 = conv_op(conv3_2, name=‘conv3_3‘, kh=3, kw=3,
 91                 n_out = 256, dh = 1, dw = 1, p = p)
 92     pool3 = mpool_op(conv3_3, name = ‘pool3‘, kh = 2, kw = 2,
 93                 dw = 2, dh = 2)
 94     # 第四块 conv4_1-conv4_2-conv4_3-pool4
 95     conv4_1 = conv_op(pool3, name=‘conv4_1‘, kh=3, kw=3,
 96                 n_out = 512, dh = 1, dw = 1, p = p)
 97     conv4_2 = conv_op(conv4_1, name=‘conv4_2‘, kh=3, kw=3,
 98                 n_out = 512, dh = 1, dw = 1, p = p)
 99     conv4_3 = conv_op(conv4_2, name=‘conv4_3‘, kh=3, kw=3,
100                 n_out = 512, dh = 1, dw = 1, p = p)
101     pool4 = mpool_op(conv4_3, name = ‘pool4‘, kh = 2, kw = 2,
102                 dw = 2, dh = 2)
103     # 第五块 conv5_1-conv5_2-conv5_3-pool5
104     conv5_1 = conv_op(pool4, name=‘conv5_1‘, kh=3, kw=3,
105                 n_out = 512, dh = 1, dw = 1, p = p)
106     conv5_2 = conv_op(conv5_1, name=‘conv5_2‘, kh=3, kw=3,
107                 n_out = 512, dh = 1, dw = 1, p = p)
108     conv5_3 = conv_op(conv5_2, name=‘conv5_3‘, kh=3, kw=3,
109                 n_out = 512, dh = 1, dw = 1, p = p)
110     pool5 = mpool_op(conv5_3, name = ‘pool5‘, kh = 2, kw = 2,
111                 dw = 2, dh = 2)
112     # 把pool5 ( [7, 7, 512] )  拉成向量
113     shp  = pool5.get_shape()
114     flattened_shape = shp[1].value * shp[2].value * shp[3].value
115     resh1 = tf.reshape(pool5, [-1, flattened_shape], name = ‘resh1‘)
116 
117     # 全连接层1 添加了 Droput来防止过拟合    
118     fc1 = fc_op(resh1, name = ‘fc1‘, n_out = 2048, p = p)
119     fc1_drop = tf.nn.dropout(fc1, keep_prob, name = ‘fc1_drop‘)
120 
121     # 全连接层2 添加了 Droput来防止过拟合    
122     fc2 = fc_op(fc1_drop, name = ‘fc2‘, n_out = 2048, p = p)
123     fc2_drop = tf.nn.dropout(fc2, keep_prob, name = ‘fc2_drop‘)
124 
125     # 全连接层3 加一个softmax求给类别的概率
126     fc3 = fc_op(fc2_drop, name = ‘fc3‘, n_out = 1000, p = p)
127     softmax = tf.nn.softmax(fc3)
128     predictions = tf.argmax(softmax, 1)
129     return predictions, softmax, fc3, p
130 
131 # 定义评测函数
132 
133 def time_tensorflow_run(session, target, feed, info_string):
134     num_steps_burn_in = 10
135     total_duration = 0.0
136     total_duration_squared = 0.0
137 
138     for i in range(num_batches + num_steps_burn_in):
139         start_time = time.time()
140         _ = session.run(target, feed_dict = feed)
141         duration = time.time() - start_time
142         if i >= num_steps_burn_in:
143             if not i  % 10: 
144                 print(‘%s: step %d, duration = %.3f‘ % 
145                     (datetime.now(), i-num_steps_burn_in, duration))
146             total_duration += duration
147             total_duration_squared += duration * duration
148     mean_dur = total_duration / num_batches 
149     var_dur = total_duration_squared / num_batches - mean_dur * mean_dur
150     std_dur = math.sqrt(var_dur)
151     print(‘%s: %s across %d steps, %.3f +/- %.3f sec / batch‘ %(datetime.now(), info_string, num_batches, mean_dur, std_dur))
152 
153 
154 def train_vgg16():
155     with tf.Graph().as_default():
156         image_size = 224  # 输入图像尺寸
157         # 生成随机数测试是否能跑通
158         #images = tf.Variable(tf.random_normal([batch_size, image_size, image_size, 3], dtype=tf.float32, stddev=1e-1))
159         with tf.device(‘/cpu:0‘):
160             images, labels = cifar10.distorted_inputs()
161         keep_prob = tf.placeholder(tf.float32)
162         prediction,softmax,fc8,p = inference_op(images,keep_prob)
163         init = tf.global_variables_initializer()
164         sess = tf.Session()
165         sess.run(init)
166         time_tensorflow_run(sess, prediction,{keep_prob:1.0}, "Forward")
167         # 用以模拟训练的过程
168         objective = tf.nn.l2_loss(fc8)  # 给一个loss
169         grad = tf.gradients(objective, p)  # 相对于loss的 所有模型参数的梯度
170         time_tensorflow_run(sess, grad, {keep_prob:0.5},"Forward-backward")
171 
172 
173 
174 
175 if __name__ == ‘__main__‘:
176     train_vgg16()