如何在Tensorflow会话运行中使用feed_dict传递图像

Question

我需要在Tensorflow中的会话运行期间传递图像

我试过了

myimage="andrew/semaphore.jpg"
mydict={'ssignals':myimage}
output = sess.run(train_prediction, feed_dict=mydict) 

但不起作用

返回错误：

Cannot interpret feed_dict key as Tensor

train_prediction张量有shape=(3, 120), dtype=float32 （120是图像分组的训练课程数量）

程序使用此方法加载并标记输入图像

def write_records_file(dataset, record_location):
    writer = None
    global counter
    global start_time

    current_index = 0
    for breed, images_filenames in dataset.items():
        for image_filename in images_filenames:
            with tf.Graph().as_default():
                with tf.Session() as sess:
                    sess.run(tf.initialize_all_variables())
                    if current_index % 100 == 0:
                        if writer:
                            writer.close()

                        record_filename = "{record_location}-{current_index}.tfrecords".format(
                            record_location=record_location,
                            current_index=current_index)
                        writer = tf.python_io.TFRecordWriter(record_filename)
                    current_index += 1

                    image_file = tf.read_file(image_filename)
                    image = tf.image.decode_jpeg(image_file)

                    grayscale_image = tf.image.rgb_to_grayscale(image)
                    resized_image = tf.image.resize_images(
                        grayscale_image, [250, 251])
                    try:
                        image_bytes = sess.run(
                            tf.cast(resized_image, tf.uint8)).tobytes()
                    except:
                        continue

                    image_label = breed.encode("utf-8")
                    example = tf.train.Example(features=tf.train.Features(feature={
                        'label': tf.train.Feature(bytes_list=tf.train.BytesList(value=[image_label])),
                        'image': tf.train.Feature(bytes_list=tf.train.BytesList(value=[image_bytes]))
                    }))
                    writer.write(example.SerializeToString())
                    counter += 1

比批量加载记录并提供CNN

修改

我没有使用相同的符号键值，请在标记之前重复注意。