如何加載由Google命名的預訓練張量流模型？

Question

我已經下載了一個名爲inception_resnet_v2_2016_08_30.ckpt一個tensorflow關卡模式。

我是否需要創建在創建此檢查點時使用的圖（包含所有變量）？

我該如何利用這一模式？

Answer 1

你們首先得到了內存中的網絡架構。你可以從here

網絡架構一旦你有了這個程序和你在一起，用下面的辦法來使用模型：

from inception_resnet_v2 import inception_resnet_v2, inception_resnet_v2_arg_scope 

height = 299 
width = 299 
channels = 3 

X = tf.placeholder(tf.float32, shape=[None, height, width, channels]) 
with slim.arg_scope(inception_resnet_v2_arg_scope()): 
    logits, end_points = inception_resnet_v2(X, num_classes=1001,is_training=False) 

有了這個，你有內存中的所有網絡，現在你可以初始化與檢查點文件（CKPT）網絡使用tf.train.saver：

saver = tf.train.Saver() 
sess = tf.Session() 
saver.restore(sess, "/home/pramod/Downloads/inception_resnet_v2_2016_08_30.ckpt") 

如果你想要做的奶瓶特徵提取，其簡單的像可以說你想從最後一層的功能，那麼只需你有申報predictions = end_points["Logits"]如果你想獲得它的其他中間層，你可以從上面的程序這些名稱inception_resnet_v2.py

之後，你可以撥打：output = sess.run(predictions, feed_dict={X:batch_images})

Answer 2

不，你不知道。

至於如何使用檢查點文件（cpkt文件）

1，本品（TensorFlow-Slim image classification library），告訴你如何從頭開始

2.後續列車模型是一個示例代碼google blog

import numpy as np 
import os 
import tensorflow as tf 
import urllib2 

from datasets import imagenet 
from nets import inception 
from preprocessing import inception_preprocessing 

slim = tf.contrib.slim 

batch_size = 3 
image_size = inception.inception_v3.default_image_size 

checkpoints_dir = '/root/code/model' 
checkpoints_filename = 'inception_resnet_v2_2016_08_30.ckpt' 
model_name = 'InceptionResnetV2' 
sess = tf.InteractiveSession() 
graph = tf.Graph() 
graph.as_default() 

def classify_from_url(url): 
    image_string = urllib2.urlopen(url).read() 
    image = tf.image.decode_jpeg(image_string, channels=3) 
    processed_image = inception_preprocessing.preprocess_image(image,  image_size, image_size, is_training=False) 
processed_images = tf.expand_dims(processed_image, 0) 

# Create the model, use the default arg scope to configure the batch norm parameters. 
with slim.arg_scope(inception.inception_resnet_v2_arg_scope()): 
    logits, _ = inception.inception_resnet_v2(processed_images, num_classes=1001, is_training=False) 
probabilities = tf.nn.softmax(logits) 

init_fn = slim.assign_from_checkpoint_fn(
    os.path.join(checkpoints_dir, checkpoints_filename), 
    slim.get_model_variables(model_name)) 

init_fn(sess) 
np_image, probabilities = sess.run([image, probabilities]) 
probabilities = probabilities[0, 0:] 
sorted_inds = [i[0] for i in sorted(enumerate(-probabilities), key=lambda x:x[1])] 

plt.figure() 
plt.imshow(np_image.astype(np.uint8)) 
plt.axis('off') 
plt.show() 

names = imagenet.create_readable_names_for_imagenet_labels() 
for i in range(5): 
    index = sorted_inds[i] 
    print('Probability %0.2f%% => [%s]' % (probabilities[index], names[index]))