tensorflow版的bvlc模型

研究相关的图片分类，偶然看到bvlc模型，但是没有tensorflow版本的，所以将caffe版本的改成了tensorflow的:

关于模型这个图：

下面贴出通用模板：

 from __future__ import print_function
 import tensorflow as tf
 import numpy as np
 from scipy.misc import imread, imresize

 class BVLG:
     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
         with tf.name_scope('conv1') as scope:
             kernel = tf.Variable(tf.truncated_normal([7, 7, 3, 96], dtype=tf.float32,
                                                      stddev=1e-1), name='weights')
             conv = tf.nn.conv2d(images, kernel, [3, 3, 1, 1], padding='SAME')
             biases = tf.Variable(tf.constant(0.0, shape=[96], dtype=tf.float32),
                                  trainable=True, name='biases')
             out = tf.nn.bias_add(conv, biases)
             self.conv1 = tf.nn.relu(out, name=scope)
             self.parameters += [kernel, biases]

         # pool1
         self.pool1 = tf.nn.max_pool(self.conv1,
                                     ksize=[1, 3, 3, 1],
                                     strides=[1, 2, 2, 1],
                                     padding='SAME',
                                     name='pool1')

         # conv2
         with tf.name_scope('conv2') as scope:
             kernel = tf.Variable(tf.truncated_normal([4, 4, 96, 256], 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=[256], 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]

         # pool2
         self.pool2 = tf.nn.max_pool(self.conv2,
                                     ksize=[1, 3, 3, 1],
                                     strides=[1, 2, 2, 1],
                                     padding='SAME',
                                     name='pool2')

         # conv5
         with tf.name_scope('conv5') 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.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.conv5 = tf.nn.relu(out, name=scope)
             self.parameters += [kernel, biases]

         # pool5
         self.pool5 = tf.nn.max_pool(self.conv5,
                                     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]

         # fc3
         with tf.name_scope('fc3') as scope:
             fc3w = tf.Variable(tf.truncated_normal([4096, 587],
                                                    dtype=tf.float32,
                                                    stddev=1e-1), name='weights')
             fc3b = tf.Variable(tf.constant(1.0, shape=[587], dtype=tf.float32),
                                trainable=True, name='biases')
             self.fc3l = tf.nn.bias_add(tf.matmul(self.fc2, fc3w), fc3b)
             self.parameters += [fc3w, fc3b]

caffe版本的ImageNet模型地址：https://github.com/BVLC/caffe/tree/master/models/bvlc_reference_caffenet