我想设计一个基于预训练网络和tensorflow构建的网络，例如以Reset50为例。 ry released a model但是，我不知道如何用它来检查我的模型？ resnet的定义可以在resnet.py中找到。谁能帮我？非常感谢你！
def inference(x, is_training,
num_classes=1000,
num_blocks=[3, 4, 6, 3], # defaults to 50-layer network
use_bias=False, # defaults to using batch norm
bottleneck=True):
c = Config()
c['bottleneck'] = bottleneck
c['is_training'] = tf.convert_to_tensor(is_training,
dtype='bool',
name='is_training')
c['ksize'] = 3
c['stride'] = 1
c['use_bias'] = use_bias
c['fc_units_out'] = num_classes
c['num_blocks'] = num_blocks
c['stack_stride'] = 2
with tf.variable_scope('scale1'):
c['conv_filters_out'] = 64
c['ksize'] = 7
c['stride'] = 2
x = conv(x, c)
x = bn(x, c)
x = activation(x)
with tf.variable_scope('scale2'):
x = _max_pool(x, ksize=3, stride=2)
c['num_blocks'] = num_blocks[0]
c['stack_stride'] = 1
c['block_filters_internal'] = 64
x = stack(x, c)
with tf.variable_scope('scale3'):
c['num_blocks'] = num_blocks[1]
c['block_filters_internal'] = 128
assert c['stack_stride'] == 2
x = stack(x, c)
with tf.variable_scope('scale4'):
c['num_blocks'] = num_blocks[2]
c['block_filters_internal'] = 256
x = stack(x, c)
with tf.variable_scope('scale5'):
c['num_blocks'] = num_blocks[3]
c['block_filters_internal'] = 512
x = stack(x, c)
# post-net
x = tf.reduce_mean(x, reduction_indices=[1, 2], name="avg_pool")
if num_classes != None:
with tf.variable_scope('fc'):
x = fc(x, c)
return x
def stack(x, c):
for n in range(c['num_blocks']):
s = c['stack_stride'] if n == 0 else 1
c['block_stride'] = s
with tf.variable_scope('block%d' % (n + 1)):
x = block(x, c)
return x
def block(x, c):
filters_in = x.get_shape()[-1]
m = 4 if c['bottleneck'] else 1
filters_out = m * c['block_filters_internal']
shortcut = x # branch 1
c['conv_filters_out'] = c['block_filters_internal']
if c['bottleneck']:
with tf.variable_scope('a'):
c['ksize'] = 1
c['stride'] = c['block_stride']
x = conv(x, c)
x = bn(x, c)
x = activation(x)
with tf.variable_scope('b'):
x = conv(x, c)
x = bn(x, c)
x = activation(x)
with tf.variable_scope('c'):
c['conv_filters_out'] = filters_out
c['ksize'] = 1
assert c['stride'] == 1
x = conv(x, c)
x = bn(x, c)
else:
with tf.variable_scope('A'):
c['stride'] = c['block_stride']
assert c['ksize'] == 3
x = conv(x, c)
x = bn(x, c)
x = activation(x)
with tf.variable_scope('B'):
c['conv_filters_out'] = filters_out
assert c['ksize'] == 3
assert c['stride'] == 1
x = conv(x, c)
x = bn(x, c)
with tf.variable_scope('shortcut'):
if filters_out != filters_in or c['block_stride'] != 1:
c['ksize'] = 1
c['stride'] = c['block_stride']
c['conv_filters_out'] = filters_out
shortcut = conv(shortcut, c)
shortcut = bn(shortcut, c)
return activation(x + shortcut)
def bn(x, c):
x_shape = x.get_shape()
params_shape = x_shape[-1:]
if c['use_bias']:
bias = _get_variable('bias', params_shape,
initializer=tf.zeros_initializer)
return x + bias
axis = list(range(len(x_shape) - 1))
beta = _get_variable('beta',
params_shape,
initializer=tf.zeros_initializer)
gamma = _get_variable('gamma',
params_shape,
initializer=tf.ones_initializer)
moving_mean = _get_variable('moving_mean',
params_shape,
initializer=tf.zeros_initializer,
trainable=False)
moving_variance = _get_variable('moving_variance',
params_shape,
initializer=tf.ones_initializer,
trainable=False)
# These ops will only be preformed when training.
mean, variance = tf.nn.moments(x, axis)
update_moving_mean = moving_averages.assign_moving_average(moving_mean,
mean, BN_DECAY)
update_moving_variance = moving_averages.assign_moving_average(
moving_variance, variance, BN_DECAY)
tf.add_to_collection(UPDATE_OPS_COLLECTION, update_moving_mean)
tf.add_to_collection(UPDATE_OPS_COLLECTION, update_moving_variance)
mean, variance = control_flow_ops.cond(
c['is_training'], lambda: (mean, variance),
lambda: (moving_mean, moving_variance))
x = tf.nn.batch_normalization(x, mean, variance, beta, gamma, BN_EPSILON)
#x.set_shape(inputs.get_shape()) ??
return x
def fc(x, c):
num_units_in = x.get_shape()[1]
num_units_out = c['fc_units_out']
weights_initializer = tf.truncated_normal_initializer(
stddev=FC_WEIGHT_STDDEV)
weights = _get_variable('weights',
shape=[num_units_in, num_units_out],
initializer=weights_initializer,
weight_decay=FC_WEIGHT_STDDEV)
biases = _get_variable('biases',
shape=[num_units_out],
initializer=tf.zeros_initializer)
x = tf.nn.xw_plus_b(x, weights, biases)
return x
def _get_variable(name,
shape,
initializer,
weight_decay=0.0,
dtype='float',
trainable=True):
"A little wrapper around tf.get_variable to do weight decay and add to"
"resnet collection"
if weight_decay > 0:
regularizer = tf.contrib.layers.l2_regularizer(weight_decay)
else:
regularizer = None
collections = [tf.GraphKeys.VARIABLES, RESNET_VARIABLES]
return tf.get_variable(name,
shape=shape,
initializer=initializer,
dtype=dtype,
regularizer=regularizer,
collections=collections,
trainable=trainable)
def conv(x, c):
ksize = c['ksize']
stride = c['stride']
filters_out = c['conv_filters_out']
filters_in = x.get_shape()[-1]
shape = [ksize, ksize, filters_in, filters_out]
initializer = tf.truncated_normal_initializer(stddev=CONV_WEIGHT_STDDEV)
weights = _get_variable('weights',
shape=shape,
dtype='float',
initializer=initializer,
weight_decay=CONV_WEIGHT_DECAY)
return tf.nn.conv2d(x, weights, [1, stride, stride, 1], padding='SAME')
def _max_pool(x, ksize=3, stride=2):
return tf.nn.max_pool(x,
ksize=[1, ksize, ksize, 1],
strides=[1, stride, stride, 1],
padding='SAME')
答案 0 :(得分：4)
基本上你应该使用为模型提供的代码。你可以使用它们创建图形，然后提供检查点文件，看看下面的ResNet50如何做到这一点：
from tensorflow.contrib.slim.nets import resnet_v1
import tensorflow as tf
import tensorflow.contrib.slim as slim
# Create graph
inputs = tf.placeholder(tf.float32, shape=[batch_size, height, width, channels])
with slim.arg_scope(resnet_v1.resnet_arg_scope()):
net, end_points = resnet_v1.resnet_v1_50(inputs, is_training=False)
saver = tf.train.Saver()
with tf.Session() as sess:
saver.restore(sess, '.resnet_v1_50.ckpt')
representation_tensor = sess.graph.get_tensor_by_name('resnet_v1_50/pool5:0') # if you don't know names like these, consider referring to corresponding model file or generate .pbtxt file as mentioned in @civilman628 's answer in link below
img = ... #load image here with size [1, 224,224, 3]
features = sess.run(representation_tensor, {'Placeholder:0': x})
有关详细信息，请参阅我的（@parthg）有关此问题的Tensorflow Github问题的答案：#7172
答案 1 :(得分：2)
我使用使用TensorFlow的keras。以下是一次输入一张图像的示例：
import numpy as np
from keras.preprocessing import image
from keras.applications import resnet50
# Load Keras' ResNet50 model that was pre-trained against the ImageNet database
model = resnet50.ResNet50()
# Load the image file, resizing it to 224x224 pixels (required by this model)
img = image.load_img("path_to_image.jpg", target_size=(224, 224))
# Convert the image to a numpy array
x = image.img_to_array(img)
# Add a forth dimension since Keras expects a list of images
x = np.expand_dims(x, axis=0)
# Scale the input image to the range used in the trained network
x = resnet50.preprocess_input(x)
# Run the image through the deep neural network to make a prediction
predictions = model.predict(x)
# Look up the names of the predicted classes. Index zero is the results for the first image.
predicted_classes = resnet50.decode_predictions(predictions, top=9)
print("This is an image of:")
for imagenet_id, name, likelihood in predicted_classes[0]:
print(" - {}: {:2f} likelihood".format(name, likelihood))