Я следую учебнику object_detection_tutorial.ipynb .
Вот код (я помещаю только те части, которые необходимы, остальная часть кода такая же, как в блокноте):
my_results = [] # I added this, a list to hold the detected classes
PATH_TO_LABELS = 'D:\\TensorFlow\\models\\research\\object_detection\\data\\oid_v4_label_map.pbtxt'
category_index = label_map_util.create_category_index_from_labelmap(PATH_TO_LABELS, use_display_name=True)
PATH_TO_TEST_IMAGES_DIR = pathlib.Path('C:\\Users\\Bhavin\\Desktop\\objects')
TEST_IMAGE_PATHS = sorted(list(PATH_TO_TEST_IMAGES_DIR.glob("*.jpg")))
TEST_IMAGE_PATHS
model = load_model()
def run_inference_for_single_image(model, image):
image = np.asarray(image)
# The input needs to be a tensor, convert it using `tf.convert_to_tensor`.
input_tensor = tf.convert_to_tensor(image)
# The model expects a batch of images, so add an axis with `tf.newaxis`.
input_tensor = input_tensor[tf.newaxis,...]
# Run inference
output_dict = model(input_tensor)
# All outputs are batches tensors.
# Convert to numpy arrays, and take index [0] to remove the batch dimension.
# We're only interested in the first num_detections.
num_detections = int(output_dict.pop('num_detections'))
output_dict = {key:value[0, :num_detections].numpy()
for key,value in output_dict.items()}
output_dict['num_detections'] = num_detections
# detection_classes should be ints.
output_dict['detection_classes'] = output_dict['detection_classes'].astype(np.int64)
# Handle models with masks:
if 'detection_masks' in output_dict:
# Reframe the the bbox mask to the image size.
detection_masks_reframed = utils_ops.reframe_box_masks_to_image_masks(
output_dict['detection_masks'], output_dict['detection_boxes'],
image.shape[0], image.shape[1])
detection_masks_reframed = tf.cast(detection_masks_reframed > 0.5,
tf.uint8)
output_dict['detection_masks_reframed'] = detection_masks_reframed.numpy()
return output_dict
def show_inference(model, image_path):
# the array based representation of the image will be used later in order to prepare the
# result image with boxes and labels on it.
image_np = np.array(Image.open(image_path))
# Actual detection.
output_dict = run_inference_for_single_image(model, image_np)
# Visualization of the results of a detection.
vis_util.visualize_boxes_and_labels_on_image_array(
image_np,
output_dict['detection_boxes'],
output_dict['detection_classes'],
output_dict['detection_scores'],
category_index,
instance_masks=output_dict.get('detection_masks_reframed', None),
use_normalized_coordinates=True,
line_thickness=8)
name = "Image" + str(i) + ".jpg"
img = Image.fromarray(image_np)
plt.imsave(name,image_np)
my_results.append(output_dict['detection_classes']) # I added this
print(my_results) # I added this
#img.show()
i = 1
for image_path in TEST_IMAGE_PATHS:
show_inference(model, image_path)
i += 1
Я проверил некоторые связанные вопросы переполнения стека и Ответ как-то связан с индексом категории . Но используемый код и примеры сильно отличаются от учебника, которым я следую.
Строка: my_results.append(output_dict['detection_classes'])
Дает вывод: [array([55], dtype=int64)]
Как мне извлечь классы обнаруженных объектов?