我已经使用 Tensorflow 对象检测 API 训练了一个更快的 rcnn 模型,并且正在将这个推理脚本与我的卡住图一起使用:
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,但使用此脚本的推理速度非常慢,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?相关的推理函数在这里,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
最佳答案
不是只传递一个大小为 (1, image_width, image_heigt, 3) 的 numpy 数组,您可以将一个包含大小为 (batch_size, image_width, image_heigt, 3) 的图像批次的 numpy 数组传递给 sess.run 命令:
output_dict = sess.run(tensor_dict, feed_dict={image_tensor: image_batch})
output_dict 会与之前略有不同,仍然没有弄清楚究竟如何。也许有人可以提供更多帮助?
编辑
似乎 output_dict 获得了另一个索引,该索引对应于您的批次中的图像编号。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
出于某种原因,这不适用于 Mask RCNN ...
关于tensorflow - 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?,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/49172643/