神经网络初始版本v3不创建标签(Neural Network Inception v3 doesn't create labels)

 我在测试神经网络初始版本v3和Tensorflow时遇到了一个错误。 
 
 我用Python这样激活并训练了模型： 
 
source tf_files/tensorflow/bin/activate
python tf_files/tensorflow/examples/image_retraining/retrain.py --bottleneck_dir=tf_files/bottlenecks --how_many_training_steps 500 --model_dir=tf_files/inception --output_graph=tf_files/retrained_graph.pb --output_labels=tf_files/retrained_labels.txt --image_dir tf_files/data
 
 这给了我以下错误： 
 
 
 
 CRITICAL：tensorflow：标签kiwi在类别测试中没有图像。 
 
 
 Kiwi是一个包含图像的文件夹。 另一个叫Apples文件夹给了我没有错误。 但也许它发生是因为它包含少于20个图像。 而且它不会创建一个名为retrained_labels.txt的文件。 
 
 所以当执行下面的命令时，它给了我一个错误，说它找不到上面提到的文件。 
 
python image_label.py apple.jpg
 
 一切都在它的文件夹中， image_label.py的内容是： 
 
import tensorflow as tf
import sys

# change this as you see fit
image_path = sys.argv[1]

# Read in the image_data
image_data = tf.gfile.FastGFile(image_path, 'rb').read()

# Loads label file, strips off carriage return
label_lines = [line.rstrip() for line 
               in tf.gfile.GFile("tf_files/retrained_labels.txt")]

# Unpersists graph from file
with tf.gfile.FastGFile("tf_files/retrained_graph.pb", 'rb') as f:
graph_def = tf.GraphDef()
graph_def.ParseFromString(f.read())
_ = tf.import_graph_def(graph_def, name='')

with tf.Session() as sess:
# Feed the image_data as input to the graph and get first prediction
softmax_tensor = sess.graph.get_tensor_by_name('final_result:0')

predictions = sess.run(softmax_tensor, \
         {'DecodeJpeg/contents:0': image_data})

# Sort to show labels of first prediction in order of confidence
top_k = predictions[0].argsort()[-len(predictions[0]):][::-1]

for node_id in top_k:
    human_string = label_lines[node_id]
    score = predictions[0][node_id]
    print('%s (score = %.5f)' % (human_string, score))

I am facing an error with testing the Neural Network Inception v3 and Tensorflow.
 
I avtivated and trained the model this way with Python:
 
source tf_files/tensorflow/bin/activate
python tf_files/tensorflow/examples/image_retraining/retrain.py --bottleneck_dir=tf_files/bottlenecks --how_many_training_steps 500 --model_dir=tf_files/inception --output_graph=tf_files/retrained_graph.pb --output_labels=tf_files/retrained_labels.txt --image_dir tf_files/data
 
Which gave me the following error:
 
 
 
CRITICAL:tensorflow:Label kiwi has no images in the category testing.
 
 
Kiwi is a folder which contains images. The other folder called Apples gave me no error. But maybe it occurs because it contains less than 20 images. And it doesn't create a file called retrained_labels.txt.
 
So when executing following following command it gives me an error saying it couldn't find the file, which is mentioned above.
 
python image_label.py apple.jpg
 
Everything is in it's folders and the content of image_label.py is:
 
import tensorflow as tf
import sys

# change this as you see fit
image_path = sys.argv[1]

# Read in the image_data
image_data = tf.gfile.FastGFile(image_path, 'rb').read()

# Loads label file, strips off carriage return
label_lines = [line.rstrip() for line 
               in tf.gfile.GFile("tf_files/retrained_labels.txt")]

# Unpersists graph from file
with tf.gfile.FastGFile("tf_files/retrained_graph.pb", 'rb') as f:
graph_def = tf.GraphDef()
graph_def.ParseFromString(f.read())
_ = tf.import_graph_def(graph_def, name='')

with tf.Session() as sess:
# Feed the image_data as input to the graph and get first prediction
softmax_tensor = sess.graph.get_tensor_by_name('final_result:0')

predictions = sess.run(softmax_tensor, \
         {'DecodeJpeg/contents:0': image_data})

# Sort to show labels of first prediction in order of confidence
top_k = predictions[0].argsort()[-len(predictions[0]):][::-1]

for node_id in top_k:
    human_string = label_lines[node_id]
    score = predictions[0][node_id]
    print('%s (score = %.5f)' % (human_string, score))

原文：https://stackoverflow.com/questions/39786320