Question

我正在将Python3与2个Nvidia 1070 Ti图形以及ubuntu 16.04上的Tensorflow 1.13一起使用，以进行实时对象检测，但是它仅使用单个GPU。因此，我尝试遍历GPU，但看起来它一次只使用一个GPU，而不是同时使用两个GPU来预测对象

##########################################################
#use multi GPU
##########################################################

detection_graph = tf.Graph()
with detection_graph.as_default():
  od_graph_def = tf.compat.v1.GraphDef()
  with tf.io.gfile.GFile(PATH_TO_CKPT, 'rb') as fid:
    serialized_graph = fid.read()
    od_graph_def.ParseFromString(serialized_graph)
    tf.import_graph_def(od_graph_def, name='')





for i, id in enumerate(['/device:GPU:0', '/device:GPU:1']):
  with tf.device(id):
          config = tf.ConfigProto()
          config.gpu_options.per_process_gpu_memory_fraction = 0.7
          sess = tf.Session(config=tf.ConfigProto(log_device_placement=True))

          with detection_graph.as_default():
                    with tf.Session(graph=detection_graph) as sess:
                      while True:
                        ret, image_np = cap.read()
                        # Expand dimensions since the model expects images to have shape: [1, None, None, 3]
                        image_np_expanded = np.expand_dims(image_np, axis=0)
                        image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
                        # Each box represents a part of the image where a particular object was detected.
                        boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
                        # Each score represent how level of confidence for each of the objects.
                        # Score is shown on the result image, together with the class label.
                        scores = detection_graph.get_tensor_by_name('detection_scores:0')
                        classes = detection_graph.get_tensor_by_name('detection_classes:0')
                        num_detections = detection_graph.get_tensor_by_name('num_detections:0')
                        # Actual detection.
                        (boxes, scores, classes, num_detections) = sess.run(
                            [boxes, scores, classes, num_detections],
                            feed_dict={image_tensor: image_np_expanded})


                        # Visualization of the results of a detection.
                        vis_util.visualize_boxes_and_labels_on_image_array(
                            image_np,
                            np.squeeze(boxes),
                            np.squeeze(classes).astype(np.int32),
                            np.squeeze(scores),
                            category_index,
                            use_normalized_coordinates=True,
                            line_thickness=8)

看起来像我使用时对于我，id枚举（['/ device：GPU：0'，'/ device：GPU：1']）：使用tf.device（id）：它只运行两次我的代码，而没有同时使用两个GPU

有解决方案吗？我对这种multigpu东西还是陌生的

使用多个GPU加载TensorFlow推理图以进行对象检测

0 个答案: