从 TensorFlow 对象检测打印对象 API

Question

我正在尝试 return 从检测中 return 得到的对象列表，或者至少是对象的名称。

我的代码：

while True: 

    ret, frame = cap.read()
    image_np = np.array(frame)
    
    input_tensor = tf.convert_to_tensor(np.expand_dims(image_np, 0), dtype=tf.float32)
    detections = detect_fn(input_tensor)
    
    num_detections = int(detections.pop('num_detections'))
    detections = {key: value[0, :num_detections].numpy()
                  for key, value in detections.items()}
    detections['num_detections'] = num_detections

    # detection_classes should be ints.
    detections['detection_classes'] = detections['detection_classes'].astype(np.int64)

    label_id_offset = 1
    image_np_with_detections = image_np.copy()

    viz_utils.visualize_boxes_and_labels_on_image_array(
                image_np_with_detections,
                detections['detection_boxes'],
                detections['detection_classes']+label_id_offset,
                detections['detection_scores'],
                category_index,
                use_normalized_coordinates=True,
                max_boxes_to_draw=1,
                min_score_thresh=.85,
                agnostic_mode=False)
    classes=detections['detection_classes'].astype(np.int64)
    scores=detections['detection_scores']
    
    #label_names = [i[0] for i in category_index.items()]
    #label_names = np.array(label_names)
    #print(label_names[detections['detection_classes']])
    
    
    
    print ([category_index.get(value) for index,value in enumerate(classes[0]) if scores[0,index] > 0.8])
    cv2.imshow('object detection',  cv2.resize(image_np_with_detections, (800, 600)))

    
    if cv2.waitKey(1) & 0xFF == ord('q'):
        cap.release()
        break

它给了我以下结果：

TypeError                                 Traceback (most recent call last)
<ipython-input-12-a749c9f2a4b4> in <module>
     37 
     38 
---> 39     print ([category_index.get(value) for index,value in enumerate(classes[0]) if scores[0,index] > 0.8])
     40     cv2.imshow('object detection',  cv2.resize(image_np_with_detections, (800, 600)))
     41 

TypeError: 'numpy.int64' object is not iterable

Answer 1

我想你想做这样的事情，

print ([category_index.get(class_) for class_, score in zip(classes, scores) if score > 0.8])

您收到的错误是因为您正在传递 classes[0]，classes 列表中的第一个元素。 enumerate().

不能迭代单个元素

作为旁注，class_ 变量以这种方式命名，因为 class 是保留关键字。 PEP8 建议在发生冲突时附加下划线。 https://www.python.org/dev/peps/pep-0008/#function-and-method-arguments

从 TensorFlow 对象检测打印对象 API

Print Objects from TensorFlow Object Detection API

python

opencv

object-detection

tensorflow