Question

我正在玩Tensorflow进行图像分类。我使用image_retraining / retrain.py来重新启动带有新类别的初始库，并使用它来使用https://github.com/llSourcell/tensorflow_image_classifier/blob/master/src/label_image.py中的label_image.py对图像进行分类，如下所示：

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("/root/tf_files/output_labels.txt")]

# Unpersists graph from file
with tf.gfile.FastGFile("/root/tf_files/output_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})
        predictions = sess.run(softmax_tensor,{'DecodePng/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))

我注意到两个问题。当我重新训练新类别时，它只训练JPG图像。我是机器学习的菜鸟，所以不确定这是一个限制还是可以训练其他扩展图像，如PNG，GIF？

另一个是在对图像进行分类时，输入再次仅用于JPG。我试图在上面的label_image.py中将DecodeJpeg更改为DecodePng，但无法正常工作。我尝试的另一种方法是将其他格式转换为JPG，然后再将它们分类为：

im = Image.open('/root/Desktop/200_s.gif').convert('RGB')
im.save('/root/Desktop/test.jpg', "JPEG")
image_path1 = '/root/Desktop/test.jpg'

还有其他办法吗？ Tensorflow是否具有处理JPG以外的其他图像格式的功能？

与@mrry

建议的JPEG相比，我通过输入解析后的图像来尝试以下操作

import tensorflow as tf
import sys
import numpy as np
from PIL import Image

# 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()

image = Image.open(image_path)
image_array = np.array(image)[:,:,0:3]  # Select RGB channels only.

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

# Unpersists graph from file
with tf.gfile.FastGFile("/root/tf_files/output_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:0': image_array})

# 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))

适用于JPEG图像但是当我使用PNG或GIF时它会抛出

        Traceback (most recent call last):   
    File "label_image.py", line 17, in <module>
        image_array = np.array(image)[:,:,0:3]  # Select RGB channels only. 
IndexError: too many indices for array

谢谢和问候

Answer 1

该模型只能训练（并评估）JPEG图像，因为您在GraphDef中保存的/root/tf_files/output_graph.pb仅包含tf.image.decode_jpeg()操作，并使用输出该操作用于进行预测。使用其他图像格式至少有几个选项：

输入已解析的图像而不是JPEG数据。在当前程序中，您将JPEG编码的图像作为张量"DecodeJpeg/contents:0"的字符串值。相反，您可以为张量"DecodeJpeg:0"（代表tf.image.decode_jpeg() op的输出）提供解码图像数据的三维数组，并且可以使用NumPy ，PIL或其他一些Python库来创建这个数组。

重新映射tf.import_graph_def()中的图像输入。 tf.import_graph_def()功能可让您通过重新映射单个张量值将两个不同的图形连接在一起。例如，您可以执行以下操作，将新的图像处理操作添加到现有图形中：

image_string_input = tf.placeholder(tf.string)
image_decoded = tf.image.decode_png(image_string_input)

# Unpersists graph from file
with tf.gfile.FastGFile("/root/tf_files/output_graph.pb", 'rb') as f:
    graph_def = tf.GraphDef()
    graph_def.ParseFromString(f.read())
    softmax_tensor, = tf.import_graph_def(
        graph_def,
        input_map={"DecodeJpeg:0": image_decoded},
        return_operations=["final_result:0"])

with tf.Session() as sess:
    # Feed the image_data as input to the graph and get first prediction
    predictions = sess.run(softmax_tensor, {image_string_input: image_data})
    # ...

Answer 2

您应该查看tf.image包。它具有很好的解码/编码JPEG，GIF和PNG的功能。

Answer 3

按照@ mrry的建议提供解析图像，将图像数据转换为数组并转换为RGB，如下面的代码中所述。现在我可以输入JPG，PNG和GIF。

+------------------------------------------+
|     Title of the slide                   |
+-------+-----------------------+----------|
|     o - First Bullet                     |
|     o - Second bullet                    |
|     o - Third bullet                     |
+------------------------------------------+ <-- End of slide 
      o - Fourth bullet    <- Out of slide
      o - Fifth  bullet    <- Out of slide

PNG，GIF等的Tensorflow Label_Image

3 个答案: