用于 PNG、GIF 等的 Tensorflow Label_Image

Question

我正在使用 Tensorflow 进行图像分类。我使用 image_retraining/retrain.py 重新训练具有新类别的初始库，并使用它使用来自https://github.com/llSourcell/tensorflow_image_classifier/blob/master/src/label_image.py 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。当我用新类别重新训练时，它只训练 JPG 图像。我是机器学习的菜鸟，所以不确定这是否是一种限制，或者是否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，输入再次仅适用于 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，然后再将它们传递给分类，例如：

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

还有其他方法可以做到这一点吗？ Tensorflow 是否具有处理除 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))

它适用于 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

Answer 1

该模型只能在 JPEG 图像上进行训练（和评估），因为您保存在 /root/tf_files/output_graph.pb 中的 GraphDef 仅包含一个 tf.image.decode_jpeg() 操作，并使用该操作的输出进行预测。使用其他图像格式至少有两种选择：

1. 输入解析的图像而不是 JPEG 数据。 在当前程序中，您输入一个 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"（表示tf.image.decode_jpeg() 操作的输出）输入解码图像数据的 3-D 数组，并且可以使用 NumPy、PIL 或其他一些 Python 库来创建这个数组。

2. 重新映射tf.import_graph_def() 中的图像输入。 tf.import_graph_def() 函数使您可以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以向现有图形添加新的图像处理操作：

   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

你应该看看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 的建议输入解析的图像，将图像数据转换为数组并转换为 RGB，如下代码所述。现在我可以输入 JPG、PNG 和 GIF。

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 = image.convert('RGB')

# 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))