Блог

При использовании API обнаружения Tensorflow API возникла проблема с более низкими значениями detection_sores, не понимаю, как улучшить detection_sores, при использовании более низких значений detection_sores получение IndexError: индекс списка вне диапазона

Нужно предложение о том, как устранить ошибку

 image_path = "C:/Users/Documents/pdf2txt/invoice.jpg"

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]
      print(output_dict['detection_scores'])
      if 'detection_masks' in output_dict:
        output_dict['detection_masks'] = output_dict['detection_masks'][0]
  return output_dict
  

Для image_path в TEST_IMAGE_PATHS:

 image = Image.open(image_path)
image_np = load_image_into_numpy_array(image)
image_np_expanded = np.expand_dims(image_np, axis=0)
output_dict = run_inference_for_single_image(image_np, detection_graph)
outImage = Image.fromarray(image_np)



firstResult = output_dict['detection_boxes'][0]
firstArray = []

score = output_dict['detection_scores'][0]
print(score)
# if score > float(0.85):
for coords in firstResult:
  realCoord = coords*1024
  firstArray.append(realCoord)

  firstImage = image.crop((firstArray[1], firstArray[0],firstArray[3],firstArray[2]))

  outputClass = output_di ct['detection_classes'][0]
  parameter =  CLASSES[outputClass - 1]
  coordText = str(firstArray[1])   " "   str(firstArray[0])   " "   str(firstArray[3])   " "  str(firstArray[2])   " "   parameter   'xout1.tif'
  coordsFile.write(coordText   "n")
  firstImage.save(r'C:/Users/neerajjha/Documents/pdf2txt/object_detection/Results/'   parameter   'xout1.tif')
  print(coordsFile)
  

ВЫВОД:

 Traceback (most recent call last):
  File "c:/Users/Documents/pdf2txt/server_detection.py", line 260, in <module>
    firstImage = image.crop((firstArray[1], firstArray[0],firstArray[3],firstArray[2]))

IndexError: list index out of range
  

Пожалуйста, предложите!!

Я думаю, что проблема в этом фрагменте кода:

 for coords in firstResult:
  realCoord = coords*1024
  firstArray.append(realCoord)

  firstImage = image.crop((firstArray[1], firstArray[0],firstArray[3],firstArray[2]))
  

Первый результат должен содержать 4 координаты ограничивающей рамки, которые обнаруживает модель. Можете ли вы попробовать переместить последнюю строку из for loop , чтобы все 4 значения были добавлены в firstArray, прежде чем использовать его в image.crop функции?