如何将NumPy数组图像转换为TensorFlow图像？

Question

使用TensorFlow的retrain.py后

https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/image_retraining/retrain.py

我已成功生成了“retrained_labels.txt”和“retrained_graph.pb”文件。对于不熟悉此过程的任何人，我基本上是按照这个教程操作的：

https://codelabs.developers.google.com/codelabs/tensorflow-for-poets/#0

这实际上是与这个受欢迎视频中的步骤相同：

https://www.youtube.com/watch?v=QfNvhPx5Px8

重新训练后，我尝试编写一个Python脚本，打开测试图像目录中的所有图像，并逐个在OpenCV窗口中显示每个图像并运行TensorFlow对其进行分类。

问题是，我无法弄清如何将图像打开为NumPy数组（这是Python OpenCV包装器使用的格式），然后将其转换为可以传递到TensorFlow的sess.run()函数中的格式。

目前，我正在使用cv2.imread()打开图像，然后再次使用tf.gfile.FastGFile()打开它。 这是一种非常糟糕的做法；我更想只打开图像一次，然后进行转换。

以下是我卡住的相关代码部分：

# open the image with OpenCV
openCVImage = cv2.imread(imageFileWithPath)

# show the OpenCV image
cv2.imshow(fileName, openCVImage)

# get the final tensor from the graph
finalTensor = sess.graph.get_tensor_by_name('final_result:0')

# open the image in TensorFlow
tfImage = tf.gfile.FastGFile(imageFileWithPath, 'rb').read()

# run the network to get the predictions
predictions = sess.run(finalTensor, {'DecodeJpeg/contents:0': tfImage})

阅读完这些帖子后：

如何将numpy数组转换为标准的TensorFlow格式？

在tensorflow中提供图像数据进行迁移学习

我尝试了以下方法：

# show the OpenCV image
cv2.imshow(fileName, openCVImage)

# get the final tensor from the graph
finalTensor = sess.graph.get_tensor_by_name('final_result:0')

# convert the NumPy array / OpenCV image to a TensorFlow image
openCVImageAsArray = np.asarray(openCVImage, np.float32)
tfImage = tf.convert_to_tensor(openCVImageAsArray, np.float32)

# run the network to get the predictions
predictions = sess.run(finalTensor, {'DecodeJpeg/contents:0': tfImage})

这会导致sess.run()行出现错误：

TypeError: The value of a feed cannot be a tf.Tensor object. Acceptable feed values include Python scalars, strings, lists, numpy ndarrays, or TensorHandles.

我也尝试过这个：

# show the OpenCV image
cv2.imshow(fileName, openCVImage)

# get the final tensor from the graph
finalTensor = sess.graph.get_tensor_by_name('final_result:0')

# convert the NumPy array / OpenCV image to a TensorFlow image
tfImage = np.array(openCVImage)[:, :, 0:3]

# run the network to get the predictions
predictions = sess.run(finalTensor, {'DecodeJpeg/contents:0': tfImage})

这将导致以下错误：

ValueError: Cannot feed value of shape (257, 320, 3) for Tensor 'DecodeJpeg/contents:0', which has shape '()'

--- 编辑 ---

我也尝试过这个：

# show the OpenCV image
cv2.imshow(fileName, openCVImage)

# get the final tensor from the graph
finalTensor = sess.graph.get_tensor_by_name('final_result:0')

# convert the NumPy array / OpenCV image to a TensorFlow image
tfImage = np.expand_dims(openCVImage, axis=0)

# run the network to get the predictions
predictions = sess.run(finalTensor, feed_dict={finalTensor: tfImage})

这会导致以下错误：

ValueError: Cannot feed value of shape (1, 669, 1157, 3) for Tensor 'final_result:0', which has shape '(?, 2)'

我也尝试过这个：

# show the OpenCV image
cv2.imshow(fileName, openCVImage)

# get the final tensor from the graph
finalTensor = sess.graph.get_tensor_by_name('final_result:0')

# convert the NumPy array / OpenCV image to a TensorFlow image
tfImage = np.expand_dims(openCVImage, axis=0)

# run the network to get the predictions
predictions = sess.run(finalTensor, feed_dict={'DecodeJpeg/contents:0': tfImage})

这会导致以下错误：

ValueError: Cannot feed value of shape (1, 669, 1157, 3) for Tensor 'DecodeJpeg/contents:0', which has shape '()'

我不确定这是否必要，但如果有人感兴趣，这里是整个脚本。请注意，除了需要两次打开图像之外，这个脚本非常好用：

# test.py

import os
import tensorflow as tf
import numpy as np
import cv2

# module-level variables ##############################################################################################
RETRAINED_LABELS_TXT_FILE_LOC = os.getcwd() + "/" + "retrained_labels.txt"
RETRAINED_GRAPH_PB_FILE_LOC = os.getcwd() + "/" + "retrained_graph.pb"

TEST_IMAGES_DIR = os.getcwd() + "/test_images"

#######################################################################################################################
def main():
    # get a list of classifications from the labels file
    classifications = []
    # for each line in the label file . . .
    for currentLine in tf.gfile.GFile(RETRAINED_LABELS_TXT_FILE_LOC):
        # remove the carriage return
        classification = currentLine.rstrip()
        # and append to the list
        classifications.append(classification)
    # end for

    # show the classifications to prove out that we were able to read the label file successfully
    print("classifications = " + str(classifications))

    # load the graph from file
    with tf.gfile.FastGFile(RETRAINED_GRAPH_PB_FILE_LOC, 'rb') as retrainedGraphFile:
        # instantiate a GraphDef object
        graphDef = tf.GraphDef()
        # read in retrained graph into the GraphDef object
        graphDef.ParseFromString(retrainedGraphFile.read())
        # import the graph into the current default Graph, note that we don't need to be concerned with the return value
        _ = tf.import_graph_def(graphDef, name='')
    # end with

    # if the test image directory listed above is not valid, show an error message and bail
    if not os.path.isdir(TEST_IMAGES_DIR):
        print("the test image directory does not seem to be a valid directory, check file / directory paths")
        return
    # end if

    with tf.Session() as sess:
        # for each file in the test images directory . . .
        for fileName in os.listdir(TEST_IMAGES_DIR):
            # if the file does not end in .jpg or .jpeg (case-insensitive), continue with the next iteration of the for loop
            if not (fileName.lower().endswith(".jpg") or fileName.lower().endswith(".jpeg")):
                continue
            # end if

            # show the file name on std out
            print(fileName)

            # get the file name and full path of the current image file
            imageFileWithPath = os.path.join(TEST_IMAGES_DIR, fileName)
            # attempt to open the image with OpenCV
            openCVImage = cv2.imread(imageFileWithPath)

            # if we were not able to successfully open the image, continue with the next iteration of the for loop
            if openCVImage is None:
                print("unable to open " + fileName + " as an OpenCV image")
                continue
            # end if

            # show the OpenCV image
            cv2.imshow(fileName, openCVImage)

            # get the final tensor from the graph
            finalTensor = sess.graph.get_tensor_by_name('final_result:0')

            # ToDo: find a way to convert from a NumPy array / OpenCV image to a TensorFlow image
            # instead of opening the file twice, these attempts don't work
            # attempt 1:
            # openCVImageAsArray = np.asarray(openCVImage, np.float32)
            # tfImage = tf.convert_to_tensor(openCVImageAsArray, np.float32)
            # attempt 2:
            # tfImage = np.array(openCVImage)[:, :, 0:3]

            # open the image in TensorFlow
            tfImage = tf.gfile.FastGFile(imageFileWithPath, 'rb').read()

            # run the network to get the predictions
            predictions = sess.run(finalTensor, {'DecodeJpeg/contents:0': tfImage})

            # sort predictions from most confidence to least confidence
            sortedPredictions = predictions[0].argsort()[-len(predictions[0]):][::-1]

            print("---------------------------------------")

            # keep track of if we're going through the next for loop for the first time so we can show more info about
            # the first prediction, which is the most likely prediction (they were sorted descending above)
            onMostLikelyPrediction = True
            # for each prediction . . .
            for prediction in sortedPredictions:
                strClassification = classifications[prediction]

                # if the classification (obtained from the directory name) ends with the letter "s", remove the "s" to change from plural to singular
                if strClassification.endswith("s"):
                    strClassification = strClassification[:-1]
                # end if

                # get confidence, then get confidence rounded to 2 places after the decimal
                confidence = predictions[0][prediction]

                # if we're on the first (most likely) prediction, state what the object appears to be and show a % confidence to two decimal places
                if onMostLikelyPrediction:
                    scoreAsAPercent = confidence * 100.0
                    print("the object appears to be a " + strClassification + ", " + "{0:.2f}".format(scoreAsAPercent) + "% confidence")
                    onMostLikelyPrediction = False
                # end if

                # for any prediction, show the confidence as a ratio to five decimal places
                print(strClassification + " (" +  "{0:.5f}".format(confidence) + ")")
            # end for

            # pause until a key is pressed so the user can see the current image (shown above) and the prediction info
            cv2.waitKey()
            # after a key is pressed, close the current window to prep for the next time around
            cv2.destroyAllWindows()
        # end for
    # end with

    # write the graph to file so we can view with TensorBoard
    tfFileWriter = tf.summary.FileWriter(os.getcwd())
    tfFileWriter.add_graph(sess.graph)
    tfFileWriter.close()

# end main

#######################################################################################################################
if __name__ == "__main__":
    main()

- cdahms

Answer 1

你的答案很接近：

{'DecodeJpeg/contents:0':tfImage} 用于解码二进制jpeg图片。

如果图片已经被解码，你需要使用{'DecodeJpeg:0': tfImage}。

点击此处阅读更多信息

所以你的代码应该像这样：

tfImage = np.array(openCVImage)[:, :, 0:3]
# run the network to get the predictions
predictions = sess.run(finalTensor, {'DecodeJpeg:0': tfImage})

- ias