ValueError：参数必须是一个密集的张量：形状为[2]，但需要[2，16]

Question

我将一个文件夹中的多个jpeg图像分类，但出现此错误：“ ValueError：参数必须是密集张量：形状为[2]，但想要为[2，16]”。我试图一次对每个图像进行推断，但我不确定自己在哪里出错。任何帮助将不胜感激！

相关代码：

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

    with tf.device('/cpu:0'):
         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 load_labels(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 read_tensor_from_image_file(images):
         image_file_path = "./test_images/"
         filenames = [os.path.join(image_file_path, filename) for 
         filename in os.listdir(image_file_path)]
         filename_queue = tf.train.string_input_producer((filenames, 
         './*.jpg'))
         image_reader = tf.WholeFileReader()
         _, image_file = image_reader.read(filename_queue)
         image_orig = tf.image.decode_jpeg(image_file, channels = 3, 
         name='jpeg_reader')
         image = tf.image.resize_images(image_orig, [299, 299])
         image = image.set_shape([299, 299, 3])
         batch_size = 1
         num_preprocess_threads = 1
         min_queue_examples = 50
         images = tf.train.shuffle_batch([image], batch_size = 
         batch_size, num_threads=num_preprocess_threads,
         capacity=min_queue_examples + 10 * batch_size, 
         min_after_dequeue=min_queue_examples)

        with tf.Session() as sess:
                tf.global_variables_initializer().run()
                coord = tf.train.Coordinator()
                threads = tf.train.start_queue_runners(coord=coord)
                image_tensor = sess.run([images])
                print(image_tensor)
                coord.request_stop()
                coord.join(threads)

def main(images):

        model_file = "tf_files/retrained_graph.pb"
        label_file = "tf_files/retrained_labels.txt"
        input_layer = "Mul"
        output_layer = "final_result"

        graph = load_graph(model_file)
        t = read_tensor_from_image_file(images)

        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);

        with tf.device('/cpu:0'):
                with tf.Session(graph=graph) as sess:
                         config = tf.ConfigProto(device_count={"CPU": 4},
                                inter_op_parallelism_threads=44,
                                intra_op_parallelism_threads=44)
        sess = tf.Session(config=config)
        start = time.time()
        results = 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(images, labels[i], results[i])

        return [images] + list(results)

if __name__ == "__main__":
             image_list = [f for f in listdir('test_images') if 
             isfile(join('test_images', f))]
             res_list = []
             for image in image_list:
                       if image.lower().endswith(('.png', '.jpg', 
                       '.jpeg', '.gif')):
                       res_list.append(main(join('test_images', 
                       image)))
                       else:
                           if not image.endswith('.jpg') or 
                       image.startswith('.'):
             continue