" 和梦想平等交易，和喧嚣保持距离。"
在Tensorflow训练模型保存时，除了常见的.ckpt格式（模型和权重分开保存的），实际部署生产时常用整合后的.pb文件，下面就讲一讲如何生成和加载.pb模型文件。
原博主地址：https://blog.csdn.net/u014432647/article/details/75276718/
感谢~
PO主的github：https://github.com/ppplinday/tensorflow-vgg16-train-and-test
其中的pitcute文件是狗和猫的图片分别15张一共30张， train那个就是训练的文件，test这个就是测试的文件。
1. train
首先说一下train。一开始当然是读图片啦。
def read_img(path):
cate = [path + x for x in os.listdir(path) if os.path.isdir(path + x)]
imgs = []
labels = []
for idx, folder in enumerate(cate):
for im in glob.glob(folder + '/*.jpg'):
print('reading the image: %s' % (im))
img = io.imread(im)
img = transform.resize(img, (w, h, c))
imgs.append(img)
labels.append(idx)
return np.asarray(imgs, np.float32), np.asarray(labels, np.int32)
data, label = read_img(path)用io.imread来读取每一张图片，然后resize成vgg的输入的大小（224，224，3），最后分别放入了data和label中。
num_example = data.shape[0]
arr = np.arange(num_example)
np.random.shuffle(arr)
data = data[arr]
label = label[arr]这里是把图片的顺序打乱，先生成一个等差数列，然后打乱，最后赋值回原来的data和label
ratio = 0.8
s = np.int(num_example * ratio)
x_train = data[:s]
y_train = label[:s]
x_val = data[s:]
y_val = label[s:]全部的数据中百分之80的用来train，剩下20的用来test（虽然一共才30张图片。。。。。）
def build_network(height, width, channel):
x = tf.placeholder(tf.float32, shape=[None, height, width, channel], name='input')
y = tf.placeholder(tf.int64, shape=[None, 2], name='labels_placeholder')
开始build相应的vgg model，这一步不难，但是每一层最好都给上相应的name。上面的x和y是相应的输入和相应的标签。
finaloutput = tf.nn.softmax(output_fc8, name="softmax")
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=finaloutput, labels=y))
optimize = tf.train.AdamOptimizer(learning_rate=1e-4).minimize(cost)
prediction_labels = tf.argmax(finaloutput, axis=1, name="output")
read_labels = y
correct_prediction = tf.equal(prediction_labels, read_labels)
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
correct_times_in_batch = tf.reduce_sum(tf.cast(correct_prediction, tf.int32))
return dict(
x=x,
y=y,
optimize=optimize,
correct_prediction=correct_prediction,
correct_times_in_batch=correct_times_in_batch,
cost=cost,
)在build的最后，是需要进行误差计算。finaloutput是最后的输出，cost是计算误差，optimize是定义训练时候安什么方式，也注意一下最后的return。
接着是训练过程。
def train_network(graph, batch_size, num_epochs, pb_file_path):
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
epoch_delta = 2
for epoch_index in range(num_epochs):
for i in range(12):
sess.run([graph['optimize']], feed_dict={
graph['x']: np.reshape(x_train[i], (1, 224, 224, 3)),
graph['y']: ([[1, 0]] if y_train[i] == 0 else [[0, 1]])
})其实训练的代码就这些，定好了batchsize和numepoch进行训练。下面的代码主要是为了看每几次相应的正确率。
constant_graph = graph_util.convert_variables_to_constants(sess, sess.graph_def, ["output"])
with tf.gfile.FastGFile(pb_file_path, mode='wb') as f:
f.write(constant_graph.SerializeToString())这两句是重要的代码，用来把训练好的模型保存为pb文件。运行完之后就会发现应该的文件夹多出了一个pb文件。
- test
def recognize(jpg_path, pb_file_path):
with tf.Graph().as_default():
output_graph_def = tf.GraphDef()
with open(pb_file_path, "rb") as f:
output_graph_def.ParseFromString(f.read())
_ = tf.import_graph_def(output_graph_def, name="")打开相应的pb文件。
img = io.imread(jpg_path)
img = transform.resize(img, (224, 224, 3))
img_out_softmax = sess.run(out_softmax, feed_dict={input_x:np.reshape(img, [-1, 224, 224, 3])})
读取图片文件，resize之后放入模型的输入位置，之后img_out_softmax就是相应输出的结果。
这大概就是整个流程。目的是为了练练手，PO主应该有挺多小错误，希望大家能够提出来让PO主好好学习哈哈哈！！！
最后放出整个的train和test的代码：
train
from PIL import Image
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
import tensorflow as tf
import os
import glob
from skimage import io, transform
from tensorflow.python.framework import graph_util
import collections
path = '/home/zhoupeilin/vgg16/picture/'
w = 224
h = 224
c = 3
def read_img(path):
cate = [path + x for x in os.listdir(path) if os.path.isdir(path + x)]
imgs = []
labels = []
for idx, folder in enumerate(cate):
for im in glob.glob(folder + '/*.jpg'):
print('reading the image: %s' % (im))
img = io.imread(im)
img = transform.resize(img, (w, h, c))
imgs.append(img)
labels.append(idx)
return np.asarray(imgs, np.float32), np.asarray(labels, np.int32)
data, label = read_img(path)
num_example = data.shape[0]
arr = np.arange(num_example)
np.random.shuffle(arr)
data = data[arr]
label = label[arr]
ratio = 0.8
s = np.int(num_example * ratio)
x_train = data[:s]
y_train = label[:s]
x_val = data[s:]
y_val = label[s:]
def build_network(height, width, channel):
x = tf.placeholder(tf.float32, shape=[None, height, width, channel], name='input')
y = tf.placeholder(tf.int64, shape=[None, 2], name='labels_placeholder')
def weight_variable(shape, name="weights"):
initial = tf.truncated_normal(shape, dtype=tf.float32, stddev=0.1)
return tf.Variable(initial, name=name)
def bias_variable(shape, name="biases"):
initial = tf.constant(0.1, dtype=tf.float32, shape=shape)
return tf.Variable(initial, name=name)
def conv2d(input, w):
return tf.nn.conv2d(input, w, [1, 1, 1, 1], padding='SAME')
def pool_max(input):
return tf.nn.max_pool(input,
ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1],
padding='SAME',
name='pool1')
def fc(input, w, b):
return tf.matmul(input, w) + b
# conv1
with tf.name_scope('conv1_1') as scope:
kernel = weight_variable([3, 3, 3, 64])
biases = bias_variable([64])
output_conv1_1 = tf.nn.relu(conv2d(x, kernel) + biases, name=scope)
with tf.name_scope('conv1_2') as scope:
kernel = weight_variable([3, 3, 64, 64])
biases = bias_variable([64])
output_conv1_2 = tf.nn.relu(conv2d(output_conv1_1, kernel) + biases, name=scope)
pool1 = pool_max(output_conv1_2)
# conv2
with tf.name_scope('conv2_1') as scope:
kernel = weight_variable([3, 3, 64, 128])
biases = bias_variable([128])
output_conv2_1 = tf.nn.relu(conv2d(pool1, kernel) + biases, name=scope)
with tf.name_scope('conv2_2') as scope:
kernel = weight_variable([3, 3, 128, 128])
biases = bias_variable([128])
output_conv2_2 = tf.nn.relu(conv2d(output_conv2_1, kernel) + biases, name=scope)
pool2 = pool_max(output_conv2_2)
# conv3
with tf.name_scope('conv3_1') as scope:
kernel = weight_variable([3, 3, 128, 256])
biases = bias_variable([256])
output_conv3_1 = tf.nn.relu(conv2d(pool2, kernel) + biases, name=scope)
with tf.name_scope('conv3_2') as scope:
kernel = weight_variable([3, 3, 256, 256])
biases = bias_variable([256])
output_conv3_2 = tf.nn.relu(conv2d(output_conv3_1, kernel) + biases, name=scope)
with tf.name_scope('conv3_3') as scope:
kernel = weight_variable([3, 3, 256, 256])
biases = bias_variable([256])
output_conv3_3 = tf.nn.relu(conv2d(output_conv3_2, kernel) + biases, name=scope)
pool3 = pool_max(output_conv3_3)
# conv4
with tf.name_scope('conv4_1') as scope:
kernel = weight_variable([3, 3, 256, 512])
biases = bias_variable([512])
output_conv4_1 = tf.nn.relu(conv2d(pool3, kernel) + biases, name=scope)
with tf.name_scope('conv4_2') as scope:
kernel = weight_variable([3, 3, 512, 512])
biases = bias_variable([512])
output_conv4_2 = tf.nn.relu(conv2d(output_conv4_1, kernel) + biases, name=scope)
with tf.name_scope('conv4_3') as scope:
kernel = weight_variable([3, 3, 512, 512])
biases = bias_variable([512])
output_conv4_3 = tf.nn.relu(conv2d(output_conv4_2, kernel) + biases, name=scope)
pool4 = pool_max(output_conv4_3)
# conv5
with tf.name_scope('conv5_1') as scope:
kernel = weight_variable([3, 3, 512, 512])
biases = bias_variable([512])
output_conv5_1 = tf.nn.relu(conv2d(pool4, kernel) + biases, name=scope)
with tf.name_scope('conv5_2') as scope:
kernel = weight_variable([3, 3, 512, 512])
biases = bias_variable([512])
output_conv5_2 = tf.nn.relu(conv2d(output_conv5_1, kernel) + biases, name=scope)
with tf.name_scope('conv5_3') as scope:
kernel = weight_variable([3, 3, 512, 512])
biases = bias_variable([512])
output_conv5_3 = tf.nn.relu(conv2d(output_conv5_2, kernel) + biases, name=scope)
pool5 = pool_max(output_conv5_3)
#fc6
with tf.name_scope('fc6') as scope:
shape = int(np.prod(pool5.get_shape()[1:]))
kernel = weight_variable([shape, 4096])
biases = bias_variable([4096])
pool5_flat = tf.reshape(pool5, [-1, shape])
output_fc6 = tf.nn.relu(fc(pool5_flat, kernel, biases), name=scope)
#fc7
with tf.name_scope('fc7') as scope:
kernel = weight_variable([4096, 4096])
biases = bias_variable([4096])
output_fc7 = tf.nn.relu(fc(output_fc6, kernel, biases), name=scope)
#fc8
with tf.name_scope('fc8') as scope:
kernel = weight_variable([4096, 2])
biases = bias_variable([2])
output_fc8 = tf.nn.relu(fc(output_fc7, kernel, biases), name=scope)
finaloutput = tf.nn.softmax(output_fc8, name="softmax")
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=finaloutput, labels=y))
optimize = tf.train.AdamOptimizer(learning_rate=1e-4).minimize(cost)
prediction_labels = tf.argmax(finaloutput, axis=1, name="output")
read_labels = y
correct_prediction = tf.equal(prediction_labels, read_labels)
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
correct_times_in_batch = tf.reduce_sum(tf.cast(correct_prediction, tf.int32))
return dict(
x=x,
y=y,
optimize=optimize,
correct_prediction=correct_prediction,
correct_times_in_batch=correct_times_in_batch,
cost=cost,
)
def train_network(graph, batch_size, num_epochs, pb_file_path):
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
epoch_delta = 2
for epoch_index in range(num_epochs):
for i in range(12):
sess.run([graph['optimize']], feed_dict={
graph['x']: np.reshape(x_train[i], (1, 224, 224, 3)),
graph['y']: ([[1, 0]] if y_train[i] == 0 else [[0, 1]])
})
if epoch_index % epoch_delta == 0:
total_batches_in_train_set = 0
total_correct_times_in_train_set = 0
total_cost_in_train_set = 0.
for i in range(12):
return_correct_times_in_batch = sess.run(graph['correct_times_in_batch'], feed_dict={
graph['x']: np.reshape(x_train[i], (1, 224, 224, 3)),
graph['y']: ([[1, 0]] if y_train[i] == 0 else [[0, 1]])
})
mean_cost_in_batch = sess.run(graph['cost'], feed_dict={
graph['x']: np.reshape(x_train[i], (1, 224, 224, 3)),
graph['y']: ([[1, 0]] if y_train[i] == 0 else [[0, 1]])
})
total_batches_in_train_set += 1
total_correct_times_in_train_set += return_correct_times_in_batch
total_cost_in_train_set += (mean_cost_in_batch * batch_size)
total_batches_in_test_set = 0
total_correct_times_in_test_set = 0
total_cost_in_test_set = 0.
for i in range(3):
return_correct_times_in_batch = sess.run(graph['correct_times_in_batch'], feed_dict={
graph['x']: np.reshape(x_val[i], (1, 224, 224, 3)),
graph['y']: ([[1, 0]] if y_val[i] == 0 else [[0, 1]])
})
mean_cost_in_batch = sess.run(graph['cost'], feed_dict={
graph['x']: np.reshape(x_val[i], (1, 224, 224, 3)),
graph['y']: ([[1, 0]] if y_val[i] == 0 else [[0, 1]])
})
total_batches_in_test_set += 1
total_correct_times_in_test_set += return_correct_times_in_batch
total_cost_in_test_set += (mean_cost_in_batch * batch_size)
acy_on_test = total_correct_times_in_test_set / float(total_batches_in_test_set * batch_size)
acy_on_train = total_correct_times_in_train_set / float(total_batches_in_train_set * batch_size)
print('Epoch - {:2d}, acy_on_test:{:6.2f}%({}/{}),loss_on_test:{:6.2f}, acy_on_train:{:6.2f}%({}/{}),loss_on_train:{:6.2f}'.format(epoch_index, acy_on_test*100.0,total_correct_times_in_test_set,
total_batches_in_test_set * batch_size,
total_cost_in_test_set,
acy_on_train * 100.0,
total_correct_times_in_train_set,
total_batches_in_train_set * batch_size,
total_cost_in_train_set))
constant_graph = graph_util.convert_variables_to_constants(sess, sess.graph_def, ["output"])
with tf.gfile.FastGFile(pb_file_path, mode='wb') as f:
f.write(constant_graph.SerializeToString())
def main():
batch_size = 12
num_epochs = 50
pb_file_path = "vggs.pb"
g = build_network(height=224, width=224, channel=3)
train_network(g, batch_size, num_epochs, pb_file_path)
main()
test：
import tensorflow as tf
import numpy as np
import PIL.Image as Image
from skimage import io, transform
def recognize(jpg_path, pb_file_path):
with tf.Graph().as_default():
output_graph_def = tf.GraphDef()
with open(pb_file_path, "rb") as f:
output_graph_def.ParseFromString(f.read())
_ = tf.import_graph_def(output_graph_def, name="")
with tf.Session() as sess:
init = tf.global_variables_initializer()
sess.run(init)
input_x = sess.graph.get_tensor_by_name("input:0")
print input_x
out_softmax = sess.graph.get_tensor_by_name("softmax:0")
print out_softmax
out_label = sess.graph.get_tensor_by_name("output:0")
print out_label
img = io.imread(jpg_path)
img = transform.resize(img, (224, 224, 3))
img_out_softmax = sess.run(out_softmax, feed_dict={input_x:np.reshape(img, [-1, 224, 224, 3])})
print "img_out_softmax:",img_out_softmax
prediction_labels = np.argmax(img_out_softmax, axis=1)
print "label:",prediction_labels
recognize("vgg16/picture/dog/dog3.jpg", "vgg16/vggs.pb")end~
加油！
扫一扫
5117
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
