是否有可以同时在批量图像上运行的 Tensorflow 对象检测 API 的推理示例版本？

Question

我已经使用 Tensorflow 对象检测 API 训练了一个更快的 rcnn 模型，并且正在将此推理脚本与我的冻结图一起使用：

https://github.com/tensorflow/models/blob/master/research/object_detection/object_detection_tutorial.ipynb

我打算将它用于视频中的对象跟踪，但使用此脚本进行推理非常慢，因为它一次只处理一个图像而不是一批图像。有没有办法一次对一批图像进行推断？相关的推理功能在这里，我想知道如何修改它以处理一堆图像

def run_inference_for_single_image(image, graph):
with graph.as_default():
    with tf.Session() as sess:
        # Get handles to input and output tensors
        ops = tf.get_default_graph().get_operations()
        all_tensor_names = {output.name for op in ops for output in op.outputs}
        tensor_dict = {}
        for key in ['num_detections', 'detection_boxes', 'detection_scores', 'detection_classes', 'detection_masks']:
            tensor_name = key + ':0'
            if tensor_name in all_tensor_names:
                tensor_dict[key] = tf.get_default_graph().get_tensor_by_name(tensor_name)
        if 'detection_masks' in tensor_dict:
            # The following processing is only for single image
            detection_boxes = tf.squeeze(tensor_dict['detection_boxes'], [0])
            detection_masks = tf.squeeze(tensor_dict['detection_masks'], [0])
            # Reframe is required to translate mask from box coordinates to image coordinates and fit the image size.
            real_num_detection = tf.cast(tensor_dict['num_detections'][0], tf.int32)
            detection_boxes = tf.slice(detection_boxes, [0, 0], [real_num_detection, -1])
            detection_masks = tf.slice(detection_masks, [0, 0, 0], [real_num_detection, -1, -1])
            detection_masks_reframed = utils_ops.reframe_box_masks_to_image_masks(detection_masks, detection_boxes, image.shape[0], image.shape[1])
            detection_masks_reframed = tf.cast(tf.greater(detection_masks_reframed, 0.5), tf.uint8)
            # Follow the convention by adding back the batch dimension
            tensor_dict['detection_masks'] = tf.expand_dims(detection_masks_reframed, 0)
        image_tensor = tf.get_default_graph().get_tensor_by_name('image_tensor:0')

        # Run inference
        output_dict = sess.run(tensor_dict, feed_dict={image_tensor: np.expand_dims(image, 0)})

        # all outputs are float32 numpy arrays, so convert types as appropriate
        output_dict['num_detections'] = int(output_dict['num_detections'][0])
        output_dict['detection_classes'] = output_dict['detection_classes'][0].astype(np.uint8)
        output_dict['detection_boxes'] = output_dict['detection_boxes'][0]
        output_dict['detection_scores'] = output_dict['detection_scores'][0]
        if 'detection_masks' in output_dict:
            output_dict['detection_masks'] = output_dict['detection_masks'][0]
return output_dict

Answer 1

如果您运行 export_inference_graph.py，您应该能够默认输入批量图像，因为它将 image_tensor 形状设置为 [None, None, None, 3]。

python object_detection/export_inference_graph.py \ --input_type image_tensor \ --pipeline_config_path ${PIPELINE_CONFIG_PATH} \ --trained_checkpoint_prefix ${TRAIN_PATH} \ --output_directory output_inference_graph.pb

Answer 2

您可以将一个带有大小为 (batch_size, image_width, image_heigt, 3) 的图像批次的 numpy 数组传递给 sess.run 命令，而不是只传递一个大小为 (1, image_width, image_heigt, 3) 的 numpy 数组：

output_dict = sess.run(tensor_dict, feed_dict={image_tensor: image_batch})

output_dict 会与之前略有不同，但还没有弄清楚到底如何。也许有人可以提供更多帮助？

编辑

似乎 output_dict 获得了另一个与您的批次中的图像编号相对应的索引。因此，您将在以下位置找到特定图像的框： output_dict['detection_boxes'][image_counter]

编辑2

由于某种原因，这不适用于 Mask RCNN...