Question

我认为在tensorflow研究文件夹中运行“单个图像推断”功能时，每次检测到（使用此代码）时，tensorflow都会创建一个会话。如何保持会话打开，并以此推断另一个图像？

我只尝试了这种“单一推断”功能，并将其循环到图像目录中。它的速度相当慢，比使用相同模型的“ cv2 =图像捕获”视频流检测要慢得多。

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

该代码将成功循环显示图像列表，但是速度很慢。我怀疑这是因为tensorflow一遍又一遍地重新加载相同的模型，因为它在每个循环中将新会话实例化到GPU中。那么如何保持会话在循环之间打开？

Answer 1

所以我转移了：

  with graph.as_default():
    with tf.Session() as sess:

要实例化循环之外的内容，但老实说，性能并没有好得多，在gtx1080上运行，使用ssd_mobilenet_v1_coco_2017_11_17模型来处理352x288图像仍需要花费一秒钟的时间。

>

有人对并行加载多张图像以进行批处理图像有任何建议吗？

奇怪的是，它使用了超过7.8GB的GPU空间来处理每个图像，我认为这可能太高了，它分配了所有可用空间，但并未实际使用它。

NVIDIA-SMI输出：

Thu Jan 31 11:33:53 2019       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 410.79       Driver Version: 410.79       CUDA Version: 10.0     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|===============================+======================+======================|
|   0  GeForce GTX 1080    Off  | 00000000:01:00.0  On |                  N/A |
| 14%   54C    P2    42W / 180W |   7879MiB /  8111MiB |      0%      Default |
+-------------------------------+----------------------+----------------------+

如图所示，该会话基本上使用了7.5GB（以PID显示），但是仅在42W功率下工作-因此，这似乎并不表示已满负荷。

有想法吗？

所有图像都是静态形状，所以也许我可以增加张量大小来分配多个图像吗？

在检测多个图像时如何保持会话打开？

1 个答案: