当我们在网上下载model文件时该怎么分析模型的图呢？？
一般情况下，我们可能下载的是*model.ckpt文件，而没有图文件model.ckpt.meta文件。如下：
这时候借鉴tensorboard的可视化或者，直接读取源码进行对图进行修改。
第一种方法(读源码):
在以下代码中，注意conv5
因为这句：
net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], scope='conv5')
所以conv5被重复三次。slim.repeat会把conv5复制3次，所以全部的参数的名称为：
有了这些参数名称我可以在构建模型时候对参数进行提取了。
有两种方法对模型进行的参数使用预训练模型数据：
1.对参数先进行随机初始化，之后进行赋值
1.1初始化：
def convlayers(self):
self.parameters = []
# zero-mean input
with tf.name_scope('preprocess') as scope:
mean = tf.constant([123.68, 116.779, 103.939], dtype=tf.float32, shape=[1, 1, 1, 3], name='img_mean')
images = self.imgs-mean
# conv1_1
with tf.name_scope('conv1_1') as scope:
kernel = tf.Variable(tf.truncated_normal([3, 3, 3, 64], dtype=tf.float32,
stddev=1e-1), name='weights')
conv = tf.nn.conv2d(images, kernel, [1, 1, 1, 1], padding='SAME')
biases = tf.Variable(tf.constant(0.0, shape=[64], dtype=tf.float32),
trainable=True, name='biases')
out = tf.nn.bias_add(conv, biases)
self.conv1_1 = tf.nn.relu(out, name=scope)
self.parameters += [kernel, biases]
1.2赋值
def load_weights(self, ‘vgg16.npy’, sess):
weights = np.load(weight_file)
keys = sorted(weights.keys())
for i, k in enumerate(keys):
print( i, k, np.shape(weights[k]))
sess.run(self.parameters[i].assign(weights[k]))
2.在进行初始化时直接进行赋值
2.1加载model数据
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
self.data_dict = np.load(’vgg16.npy‘, encoding='latin1').item()
2.2赋值给参数
conv4_1 = self.conv_layer(pool3, "conv4_1")
以上均是在读源码文件时候知道参数名称。
第二种方法(可视化)：
这种方法其实是对源码有一定了解之后在进行的操作，但在操作上会直观一些。
上图吧：
上面图中有我选的是pool5是，在pool5的下面是conv5，conv5其实有三个卷积看下面：
每个节点的名字均可以看到，conv5_1，conv5_2，conv5_3.等
现在我们可以进行对参数进行提取了，与上面类似。
下面是tensorflow的官方代码：
def vgg_16(inputs,
num_classes=1000,
is_training=True,
dropout_keep_prob=0.5,
spatial_squeeze=True,
scope='vgg_16',
fc_conv_padding='VALID',
global_pool=False):
"""Oxford Net VGG 16-Layers version D Example.
Note: All the fully_connected layers have been transformed to conv2d layers.
To use in classification mode, resize input to 224x224.
Args:
inputs: a tensor of size [batch_size, height, width, channels].
num_classes: number of predicted classes. If 0 or None, the logits layer is
omitted and the input features to the logits layer are returned instead.
is_training: whether or not the model is being trained.
dropout_keep_prob: the probability that activations are kept in the dropout
layers during training.
spatial_squeeze: whether or not should squeeze the spatial dimensions of the
outputs. Useful to remove unnecessary dimensions for classification.
scope: Optional scope for the variables.
fc_conv_padding: the type of padding to use for the fully connected layer
that is implemented as a convolutional layer. Use 'SAME' padding if you
are applying the network in a fully convolutional manner and want to
get a prediction map downsampled by a factor of 32 as an output.
Otherwise, the output prediction map will be (input / 32) - 6 in case of
'VALID' padding.
global_pool: Optional boolean flag. If True, the input to the classification
layer is avgpooled to size 1x1, for any input size. (This is not part
of the original VGG architecture.)
Returns:
net: the output of the logits layer (if num_classes is a non-zero integer),
or the input to the logits layer (if num_classes is 0 or None).
end_points: a dict of tensors with intermediate activations.
"""
with tf.variable_scope(scope, 'vgg_16', [inputs]) as sc:
end_points_collection = sc.original_name_scope + '_end_points'
# Collect outputs for conv2d, fully_connected and max_pool2d.
with slim.arg_scope([slim.conv2d, slim.fully_connected, slim.max_pool2d],
outputs_collections=end_points_collection):
net = slim.repeat(inputs, 2, slim.conv2d, 64, [3, 3], scope='conv1')
net = slim.max_pool2d(net, [2, 2], scope='pool1')
net = slim.repeat(net, 2, slim.conv2d, 128, [3, 3], scope='conv2')
net = slim.max_pool2d(net, [2, 2], scope='pool2')
net = slim.repeat(net, 3, slim.conv2d, 256, [3, 3], scope='conv3')
net = slim.max_pool2d(net, [2, 2], scope='pool3')
net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], scope='conv4')
net = slim.max_pool2d(net, [2, 2], scope='pool4')
net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], scope='conv5')
net = slim.max_pool2d(net, [2, 2], scope='pool5')
# Use conv2d instead of fully_connected layers.
net = slim.conv2d(net, 4096, [7, 7], padding=fc_conv_padding, scope='fc6')
net = slim.dropout(net, dropout_keep_prob, is_training=is_training,
scope='dropout6')
net = slim.conv2d(net, 4096, [1, 1], scope='fc7')
# Convert end_points_collection into a end_point dict.
end_points = slim.utils.convert_collection_to_dict(end_points_collection)
if global_pool:
net = tf.reduce_mean(net, [1, 2], keep_dims=True, name='global_pool')
end_points['global_pool'] = net
if num_classes:
net = slim.dropout(net, dropout_keep_prob, is_training=is_training,
scope='dropout7')
net = slim.conv2d(net, num_classes, [1, 1],
activation_fn=None,
normalizer_fn=None,
scope='fc8')
if spatial_squeeze and num_classes is not None:
net = tf.squeeze(net, [1, 2], name='fc8/squeezed')
end_points[sc.name + '/fc8'] = net
return net, end_points
vgg_16.default_image_size = 224
莫烦python的二分类
#!/usr/bin/python3
# -*- coding: utf-8 -*-
# @Time : 2018/5/27 9:50
# @Author : yanghe
# @File : vgg16_test.py
from urllib.request import urlretrieve
import os
import numpy as np
import tensorflow as tf
import skimage.io
import skimage.transform
import matplotlib.pyplot as plt
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')
def load_img(path):
img = skimage.io.imread(path)
img = img / 255.0
# print "Original Image Shape: ", img.shape
# we crop image from center
short_edge = min(img.shape[:2])
yy = int((img.shape[0] - short_edge) / 2)
xx = int((img.shape[1] - short_edge) / 2)
crop_img = img[yy: yy + short_edge, xx: xx + short_edge]
# resize to 224, 224
resized_img = skimage.transform.resize(crop_img, (224, 224))[None, :, :, :] # shape [1, 224, 224, 3]
return resized_img
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
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 at here https://mega.nz/#!YU1FWJrA!O1ywiCS2IiOlUCtCpI6HTJOMrneN-Qdv3ywQP5poecM')
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)
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
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()
以下是对先进行随机初始化在进行赋值操作
# -*- coding: utf-8 -*-
"""
Created on Thu Sep 6 17:37:30 2018
@author: yanghe
"""
########################################################################################
# Davi Frossard, 2016 #
# VGG16 implementation in TensorFlow #
# Details: #
# http://www.cs.toronto.edu/~frossard/post/vgg16/ #
# #
# Model from https://gist.github.com/ksimonyan/211839e770f7b538e2d8#file-readme-md #
# Weights from Caffe converted using https://github.com/ethereon/caffe-tensorflow #
########################################################################################
import tensorflow as tf
import numpy as np
from scipy.misc import imread, imresize
from imagenet_classes import class_names
class vgg16:
def __init__(self, imgs, weights=None, sess=None):
self.imgs = imgs
self.convlayers()
self.fc_layers()
self.probs = tf.nn.softmax(self.fc3l)
if weights is not None and sess is not None:
self.load_weights(weights, sess)
def convlayers(self):
self.parameters = []
# zero-mean input
with tf.name_scope('preprocess') as scope:
mean = tf.constant([123.68, 116.779, 103.939], dtype=tf.float32, shape=[1, 1, 1, 3], name='img_mean')
images = self.imgs-mean
# conv1_1
with tf.name_scope('conv1_1') as scope:
kernel = tf.Variable(tf.truncated_normal([3, 3, 3, 64], dtype=tf.float32,
stddev=1e-1), name='weights')
conv = tf.nn.conv2d(images, kernel, [1, 1, 1, 1], padding='SAME')
biases = tf.Variable(tf.constant(0.0, shape=[64], dtype=tf.float32),
trainable=True, name='biases')
out = tf.nn.bias_add(conv, biases)
self.conv1_1 = tf.nn.relu(out, name=scope)
self.parameters += [kernel, biases]
# conv1_2
with tf.name_scope('conv1_2') as scope:
kernel = tf.Variable(tf.truncated_normal([3, 3, 64, 64], dtype=tf.float32,
stddev=1e-1), name='weights')
conv = tf.nn.conv2d(self.conv1_1, kernel, [1, 1, 1, 1], padding='SAME')
biases = tf.Variable(tf.constant(0.0, shape=[64], dtype=tf.float32),
trainable=True, name='biases')
out = tf.nn.bias_add(conv, biases)
self.conv1_2 = tf.nn.relu(out, name=scope)
self.parameters += [kernel, biases]
# pool1
self.pool1 = tf.nn.max_pool(self.conv1_2,
ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1],
padding='SAME',
name='pool1')
# conv2_1
with tf.name_scope('conv2_1') as scope:
kernel = tf.Variable(tf.truncated_normal([3, 3, 64, 128], dtype=tf.float32,
stddev=1e-1), name='weights')
conv = tf.nn.conv2d(self.pool1, kernel, [1, 1, 1, 1], padding='SAME')
biases = tf.Variable(tf.constant(0.0, shape=[128], dtype=tf.float32),
trainable=True, name='biases')
out = tf.nn.bias_add(conv, biases)
self.conv2_1 = tf.nn.relu(out, name=scope)
self.parameters += [kernel, biases]
# conv2_2
with tf.name_scope('conv2_2') as scope:
kernel = tf.Variable(tf.truncated_normal([3, 3, 128, 128], dtype=tf.float32,
stddev=1e-1), name='weights')
conv = tf.nn.conv2d(self.conv2_1, kernel, [1, 1, 1, 1], padding='SAME')
biases = tf.Variable(tf.constant(0.0, shape=[128], dtype=tf.float32),
trainable=True, name='biases')
out = tf.nn.bias_add(conv, biases)
self.conv2_2 = tf.nn.relu(out, name=scope)
self.parameters += [kernel, biases]
# pool2
self.pool2 = tf.nn.max_pool(self.conv2_2,
ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1],
padding='SAME',
name='pool2')
# conv3_1
with tf.name_scope('conv3_1') as scope:
kernel = tf.Variable(tf.truncated_normal([3, 3, 128, 256], dtype=tf.float32,
stddev=1e-1), name='weights')
conv = tf.nn.conv2d(self.pool2, kernel, [1, 1, 1, 1], padding='SAME')
biases = tf.Variable(tf.constant(0.0, shape=[256], dtype=tf.float32),
trainable=True, name='biases')
out = tf.nn.bias_add(conv, biases)
self.conv3_1 = tf.nn.relu(out, name=scope)
self.parameters += [kernel, biases]
# conv3_2
with tf.name_scope('conv3_2') as scope:
kernel = tf.Variable(tf.truncated_normal([3, 3, 256, 256], dtype=tf.float32,
stddev=1e-1), name='weights')
conv = tf.nn.conv2d(self.conv3_1, kernel, [1, 1, 1, 1], padding='SAME')
biases = tf.Variable(tf.constant(0.0, shape=[256], dtype=tf.float32),
trainable=True, name='biases')
out = tf.nn.bias_add(conv, biases)
self.conv3_2 = tf.nn.relu(out, name=scope)
self.parameters += [kernel, biases]
# conv3_3
with tf.name_scope('conv3_3') as scope:
kernel = tf.Variable(tf.truncated_normal([3, 3, 256, 256], dtype=tf.float32,
stddev=1e-1), name='weights')
conv = tf.nn.conv2d(self.conv3_2, kernel, [1, 1, 1, 1], padding='SAME')
biases = tf.Variable(tf.constant(0.0, shape=[256], dtype=tf.float32),
trainable=True, name='biases')
out = tf.nn.bias_add(conv, biases)
self.conv3_3 = tf.nn.relu(out, name=scope)
self.parameters += [kernel, biases]
# pool3
self.pool3 = tf.nn.max_pool(self.conv3_3,
ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1],
padding='SAME',
name='pool3')
# conv4_1
with tf.name_scope('conv4_1') as scope:
kernel = tf.Variable(tf.truncated_normal([3, 3, 256, 512], dtype=tf.float32,
stddev=1e-1), name='weights')
conv = tf.nn.conv2d(self.pool3, kernel, [1, 1, 1, 1], padding='SAME')
biases = tf.Variable(tf.constant(0.0, shape=[512], dtype=tf.float32),
trainable=True, name='biases')
out = tf.nn.bias_add(conv, biases)
self.conv4_1 = tf.nn.relu(out, name=scope)
self.parameters += [kernel, biases]
# conv4_2
with tf.name_scope('conv4_2') as scope:
kernel = tf.Variable(tf.truncated_normal([3, 3, 512, 512], dtype=tf.float32,
stddev=1e-1), name='weights')
conv = tf.nn.conv2d(self.conv4_1, kernel, [1, 1, 1, 1], padding='SAME')
biases = tf.Variable(tf.constant(0.0, shape=[512], dtype=tf.float32),
trainable=True, name='biases')
out = tf.nn.bias_add(conv, biases)
self.conv4_2 = tf.nn.relu(out, name=scope)
self.parameters += [kernel, biases]
# conv4_3
with tf.name_scope('conv4_3') as scope:
kernel = tf.Variable(tf.truncated_normal([3, 3, 512, 512], dtype=tf.float32,
stddev=1e-1), name='weights')
conv = tf.nn.conv2d(self.conv4_2, kernel, [1, 1, 1, 1], padding='SAME')
biases = tf.Variable(tf.constant(0.0, shape=[512], dtype=tf.float32),
trainable=True, name='biases')
out = tf.nn.bias_add(conv, biases)
self.conv4_3 = tf.nn.relu(out, name=scope)
self.parameters += [kernel, biases]
# pool4
self.pool4 = tf.nn.max_pool(self.conv4_3,
ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1],
padding='SAME',
name='pool4')
# conv5_1
with tf.name_scope('conv5_1') as scope:
kernel = tf.Variable(tf.truncated_normal([3, 3, 512, 512], dtype=tf.float32,
stddev=1e-1), name='weights')
conv = tf.nn.conv2d(self.pool4, kernel, [1, 1, 1, 1], padding='SAME')
biases = tf.Variable(tf.constant(0.0, shape=[512], dtype=tf.float32),
trainable=True, name='biases')
out = tf.nn.bias_add(conv, biases)
self.conv5_1 = tf.nn.relu(out, name=scope)
self.parameters += [kernel, biases]
# conv5_2
with tf.name_scope('conv5_2') as scope:
kernel = tf.Variable(tf.truncated_normal([3, 3, 512, 512], dtype=tf.float32,
stddev=1e-1), name='weights')
conv = tf.nn.conv2d(self.conv5_1, kernel, [1, 1, 1, 1], padding='SAME')
biases = tf.Variable(tf.constant(0.0, shape=[512], dtype=tf.float32),
trainable=True, name='biases')
out = tf.nn.bias_add(conv, biases)
self.conv5_2 = tf.nn.relu(out, name=scope)
self.parameters += [kernel, biases]
# conv5_3
with tf.name_scope('conv5_3') as scope:
kernel = tf.Variable(tf.truncated_normal([3, 3, 512, 512], dtype=tf.float32,
stddev=1e-1), name='weights')
conv = tf.nn.conv2d(self.conv5_2, kernel, [1, 1, 1, 1], padding='SAME')
biases = tf.Variable(tf.constant(0.0, shape=[512], dtype=tf.float32),
trainable=True, name='biases')
out = tf.nn.bias_add(conv, biases)
self.conv5_3 = tf.nn.relu(out, name=scope)
self.parameters += [kernel, biases]
# pool5
self.pool5 = tf.nn.max_pool(self.conv5_3,
ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1],
padding='SAME',
name='pool4')
def fc_layers(self):
# fc1
with tf.name_scope('fc1') as scope:
shape = int(np.prod(self.pool5.get_shape()[1:]))
fc1w = tf.Variable(tf.truncated_normal([shape, 4096],
dtype=tf.float32,
stddev=1e-1), name='weights')
fc1b = tf.Variable(tf.constant(1.0, shape=[4096], dtype=tf.float32),
trainable=True, name='biases')
pool5_flat = tf.reshape(self.pool5, [-1, shape])
fc1l = tf.nn.bias_add(tf.matmul(pool5_flat, fc1w), fc1b)
self.fc1 = tf.nn.relu(fc1l)
self.parameters += [fc1w, fc1b]
# fc2
with tf.name_scope('fc2') as scope:
fc2w = tf.Variable(tf.truncated_normal([4096, 4096],
dtype=tf.float32,
stddev=1e-1), name='weights')
fc2b = tf.Variable(tf.constant(1.0, shape=[4096], dtype=tf.float32),
trainable=True, name='biases')
fc2l = tf.nn.bias_add(tf.matmul(self.fc1, fc2w), fc2b)
self.fc2 = tf.nn.relu(fc2l)
self.parameters += [fc2w, fc2b]
# fc3
with tf.name_scope('fc3') as scope:
fc3w = tf.Variable(tf.truncated_normal([4096, 1000],
dtype=tf.float32,
stddev=1e-1), name='weights')
fc3b = tf.Variable(tf.constant(1.0, shape=[1000], dtype=tf.float32),
trainable=True, name='biases')
self.fc3l = tf.nn.bias_add(tf.matmul(self.fc2, fc3w), fc3b)
self.parameters += [fc3w, fc3b]
def load_weights(self, weight_file, sess):
weights = np.load(weight_file)
keys = sorted(weights.keys())
for i, k in enumerate(keys):
print( i, k, np.shape(weights[k]))
sess.run(self.parameters[i].assign(weights[k]))
if __name__ == '__main__':
sess = tf.Session()
imgs = tf.placeholder(tf.float32, [None, 224, 224, 3])
vgg = vgg16(imgs, 'vgg16_weights.npz', sess)
img1 = imread('laska.png', mode='RGB')
img1 = imresize(img1, (224, 224))
prob = sess.run(vgg.probs, feed_dict={vgg.imgs: [img1]})[0]
preds = (np.argsort(prob)[::-1])[0:5]
for p in preds:
print( class_names[p], prob[p])
对导入的np矩阵文件进行操作
from model import Model
import tensorflow as tf
from imagenet_classes import class_names
import numpy as np
# from imagenet_classes import class_names
from scipy.misc import imread, imresize
from PIL import Image
class Vgg16(Model):
def __init__(self):
self.inputs_placeholder = None
self.labels_placeholder = None
self.build()
def load_weights(self, weights_file, sess):
weights = np.load(weights_file)
keys = sorted(weights.keys())
variables = tf.global_variables()[:len(keys)]
for i, k in enumerate(keys):
print(i, k, np.shape(keys), variables[i].name)
sess.run(variables[i].assign(weights[k]))
def add_conv3(self, inputs, num_filters, activation_fn=tf.nn.relu, scope=None):
'''
CONV3
kernel_size=3
'''
return tf.contrib.layers.conv2d(
inputs=inputs,
num_outputs=num_filters,
kernel_size=3,
padding='SAME',
activation_fn=activation_fn,
scope=scope
)
def add_max_pool(self, inputs):
return tf.contrib.layers.max_pool2d(
inputs=inputs,
kernel_size=2,
stride=2,
padding='VALID',
)
def add_fc(self, inputs, num_outputs, activation_fn=tf.nn.relu, scope=None):
return tf.contrib.layers.fully_connected(
inputs=inputs,
num_outputs=num_outputs,
scope=scope,
activation_fn=activation_fn
)
def add_prediction_op(self):
X = self.inputs_placeholder # 224x224x3
vgg_mean = tf.constant([123.68, 116.779, 103.939], dtype=tf.float32, shape=(1, 1, 1, 3), name='vgg_mean')
X -= vgg_mean
with tf.name_scope('conv1_1') as scope:
a = self.add_conv3(X, 64, scope=scope)
with tf.name_scope('conv1_2') as scope:
a = self.add_conv3(a, 64, scope=scope)
a = self.add_max_pool(a)
with tf.name_scope('conv2_1') as scope:
a = self.add_conv3(a, 128, scope=scope)
with tf.name_scope('conv2_2') as scope:
a = self.add_conv3(a, 128, scope=scope)
a = self.add_max_pool(a)
with tf.name_scope('conv3_1') as scope:
a = self.add_conv3(a, 256, scope=scope)
with tf.name_scope('conv3_2') as scope:
a = self.add_conv3(a, 256, scope=scope)
with tf.name_scope('conv3_3') as scope:
a = self.add_conv3(a, 256, scope=scope)
a = self.add_max_pool(a)
with tf.name_scope('conv4_1') as scope:
a = self.add_conv3(a, 512, scope=scope)
with tf.name_scope('conv4_2') as scope:
a = self.add_conv3(a, 512, scope=scope)
with tf.name_scope('conv4_3') as scope:
a = self.add_conv3(a, 512, scope=scope)
a = self.add_max_pool(a)
with tf.name_scope('conv5_1') as scope:
a = self.add_conv3(a, 512, scope=scope)
with tf.name_scope('conv5_2') as scope:
a = self.add_conv3(a, 512, scope=scope)
with tf.name_scope('conv5_3') as scope:
a = self.add_conv3(a, 512, scope=scope)
a = self.add_max_pool(a)
a = tf.contrib.layers.flatten(a)
with tf.name_scope('fc6') as scope:
a = self.add_fc(a, 4096, scope=scope)
with tf.name_scope('fc7') as scope:
a = self.add_fc(a, 4096, scope=scope)
with tf.name_scope('fc8') as scope:
a = self.add_fc(a, 1000, None, scope)
pred = a
return pred
def add_placeholders(self):
self.inputs_placeholder = tf.placeholder(tf.float32, shape=(None, 224,224, 3))
def create_feed_dict(self, inputs_batch, labels_batch=None):
feed_dict = {
self.inputs_placeholder : inputs_batch,
}
if labels_batch is not None:
feed_dict[self.labels_placeholder] = labels_batch
return feed_dict
def predict(self, sess, inputs):
'''
The step to predict the image
'''
feed_dict = self.create_feed_dict(inputs)
prob = sess.run(tf.nn.softmax(self.pred), feed_dict)
# preds = np.argmax(prob, axis=1)
return prob
def add_loss_op(self, pred):
return None
def add_training_op(self, loss):
pass
if __name__=='__main__':
img = Image.open('cat.1.jpg').resize((224,224))
print(img)
model = Vgg16()
# print([x.name for x in tf.global_variables()])
# img = imread('laska.png', mode='RGB')
# img = imresize(img, (224,224))
X = np.array([np.asarray(img), np.asarray(img)])
# X = (X - X.mean(axis=0)) / X.std(axis=0)
print(X.shape)
with tf.Session() as sess:
model.load_weights('../vgg16_weights.npz', sess)
prob = model.predict(sess, X)
preds = (np.argsort(prob)[0][0][::-1])[0:5]
print(preds)
for p in preds:
print( class_names[p], prob[p])
下面是导入*model.ckpt文件时操作
# -*- coding: utf-8 -*-
"""
Created on Fri Sep 7 19:44:44 2018
@author: yanghe
"""
import tensorflow as tf
import tensorflow.contrib.slim as slim
import tensorflow.contrib.slim.nets as nets
#from tensorflow.contrib.slim.nets.inception import inception_v3, inception_v3_arg_scope
import numpy as np
height = 224
width = 224
channels = 3
num_classes=1000
X = tf.placeholder(tf.float32, shape=[None, height, width, channels])
y = tf.placeholder(tf.float32,shape=[None,182])
with slim.arg_scope(nets.vgg.vgg_arg_scope()):
logits, end_points = nets.vgg.vgg_16(X, num_classes=num_classes,is_training=False)
exclude=[]
variables_to_restore=slim.get_variables_to_restore()
'''
for v in variables_to_restore:
if 'Mixed_7c' not in v.name:
exclude.append(v)
'''
saver = tf.train.Saver()
with tf.Session() as sess:
saver.restore(sess,'./vgg_16.ckpt')
writer = tf.summary.FileWriter('./logs', sess.graph)
writer.close()
shape=logits.get_shape().as_list()
dim=1
for d in shape[1:]:
dim*=d
fc_=tf.reshape(logits,[-1,dim])
#修改最后面的fc8需要进行微调 fc0_weights=tf.get_variable(name="vgg_16/fc8/weights",shape=(1000,2),initializer=tf.contrib.layers.xavier_initializer())
fc0_biases=tf.get_variable(name="vgg_16/fc8/biases",shape=(2),initializer=tf.contrib.layers.xavier_initializer())
logits_=tf.nn.bias_add(tf.matmul(fc_,fc0_weights),fc0_biases)
predictions=tf.nn.softmax(logits_)
#cross_entropy = -tf.reduce_sum(y*tf.log(predictions))
cross_entropy=tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=logits_))
#cross_entropy_mean=tf.reduce_mean(cross_entropy)
train_step=tf.train.GradientDescentOptimizer(1e-6).minimize(cross_entropy)
correct_pred=tf.equal(tf.argmax(y,1),tf.argmax(predictions,1))
#acc=tf.reduce_sum(tf.cast(correct_pred,tf.float32))
accuracy=tf.reduce_mean(tf.cast(correct_pred,tf.float32))
with tf.Session() as sess:
o_dir="E:/test"
num_classes=182
batch_size=3
epoches=2
batches=img_convert.data_lrn(img_convert.load_data(o_dir,num_classes,batch_size))
sess.run(tf.global_variables_initializer())
saver=tf.train.Saver(variables_to_restore)
saver.restore(sess,os.path.join("E:\\","inception_v3.ckpt"))
for epoch in range(epoches):
for batch in batches:
sess.run(train_step,feed_dict={X:batch[0],y:batch[1]})
acc=sess.run(accuracy,feed_dict={X:batches[0][0],y:batches[1][1]})
print(acc)
print("Done")