尝试使用Tensorflow中的输入队列对一批图像进行分类时出错

Question

我正在尝试使用输入队列在目录“ test_images”中将jpeg格式的多个图像分类。我认为最好的选择是使用输入队列来输入这些图像并对其进行分类（最好是批量）。但是，当我尝试执行此操作时，出现错误：“无法将类型的对象转换为Tensor”。任何建议如何解决此问题将不胜感激！

这是代码：

  class image_recognition_algorithm():

def __init__(self, file_name, model_file, label_file):
    self.model_file = model_file
    self.label_file = label_file
    self.file_name = file_name

def load_graph(self):
    graph = tf.Graph()
    graph_def = tf.GraphDef()

    with open(model_file, "rb") as f:
        graph_def.ParseFromString(f.read())
    with graph.as_default():
        tf.import_graph_def(graph_def)

    return graph

def read_images_from_file(self, input_queue, input_height=299, input_width=299,
                input_mean=128, input_std=128):
    input_queue = "file_contents"
    output_name = "normalized"
    input_queue = [f for f in listdir('test_images') if isfile(join('test_images', f))]
    file_contents = tf.read_file(input_queue[0])
    image_reader = tf.image.decode_jpeg(file_contents, channels=3)
    float_caster = tf.expand_dims(image_reader, tf.float32)
    dims_expander = tf.expand_dims(float_caster, 0);
    resized = tf.image.resize_bilinear(dims_expander, [input_height, input_width])
    normalized = tf.divide(tf.subtract(resized, [input_mean]), [input_std])
    images = tf.convert_to_tensor(image_list)
    input_queue = tf.train.slice_input_producer([images], shuffle=True)
    image = read_images_from_file(input_queue)
    image = preprocess_image(image)

    image_batch = tf.train.batch([image], batch_size=5)

    sess = tf.Session()
    result = sess.run(image)

    return result

def load_labels(self, label_file):
    label = []
    proto_as_ascii_lines = tf.gfile.GFile(label_file).readlines()
    for l in proto_as_ascii_lines:
        label.append(l.rstrip())
    return label

def main(self, file_name):
    self.model_file = "tf_files/retrained_graph.pb"
    self.label_file = "tf_files/retrained_labels.txt"
    input_layer = "Mul"
    output_layer = "final_result"

    graph = self.load_graph()

    res_list = []
    for f in file_name:
        t = self.read_images_from_file(f)

        input_name = "import/" + input_layer
        output_name = "import/" + output_layer
        input_operation = graph.get_operation_by_name(input_name);
        output_operation = graph.get_operation_by_name(output_name);
        config = tf.ConfigProto(device_count={"CPU": 4},
                                inter_op_parallelism_threads=1,
                                intra_op_parallelism_threads=4)
        self.sess = tf.Session(graph=graph, config=config)
        start = time.time()
        results = self.sess.run(output_operation.outputs[0],
                          {input_operation.outputs[0]: t})
        end=time.time()
        results = np.squeeze(results)

        top_k = results.argsort()[-5:][::-1]
        labels = load_labels(label_file)

        print('\nEvaluation time (1-image): {:.3f}s\n'.format(end-start))

        for i in top_k:
            print(file_name, labels[i], results[i])

        return [file_names] + list(results)

        res_list = [f for f in listdir('test_images') if isfile(join('test_images', f))]

        for image in res_list:
            if image.lower().endswith(('.png', '.jpg', '.jpeg', '.gif')):
                res_list.append(join('test_images', image))

        return res_list


if __name__ == '__main__':
     model_file = "tf_files/retrained_graph.pb"
     label_file = "tf_files/retrained_labels.txt"
     file_name = [f for f in listdir('test_images') if 
                     isfile(join('test_images', f))]
     image_recognition_algorithm_obj = 
     image_recognition_algorithm(model_file, label_file, file_name)
     image_recognition_algorithm_obj.main(file_name)