Error in implemeting tensorflow object detection model-CodePudding

I am new to learning object detection using tensorflow, I am implementing a model with reference to this site https://www.mygreatlearning.com/blog/object-detection-using-tensorflow/ I have followed all steps but there are two prominent errors that come again and again,the first one is

"INFO:tensorflow:Saver not created because there are no variables in the graph to restore" when running these two commands

model_name = 'ssd_inception_v2_coco_2017_11_17'
detection_model = load_model(model_name)

another error is TypeError: int() argument must be a string, a bytes-like object or a number, not 'Tensor' on running these

for image_path in TEST_IMAGE_PATHS:
    print(image_path)
    show_inference(detection_model, image_path)

this is the call stack:

models\research\object_detection\test_images\image1.jpg
---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-20-e230477d58de> in <module>
      1 for image_path in TEST_IMAGE_PATHS:
      2     print(image_path)
----> 3     show_inference(detection_model, image_path)

<ipython-input-18-a9efdd893038> in show_inference(model, image_path)
      7     # Actual detection.
      8 
----> 9     output_dict = run_inference_for_single_image(model, image_np)
     10     # Visualization of the results of a detection.
     11     vis_util.visualize_boxes_and_labels_on_image_array(

<ipython-input-17-7172365aecd9> in run_inference_for_single_image(model, image)
     12     # Convert to numpy arrays, and take index [0] to remove the batch dimension.
     13     # We're only interested in the first num_detections.
---> 14     num_detections = int(output_dict.pop('num_detections'))
     15 
     16     #num_detections = int(tf.get_static_value(output_dict.pop('num_detections'))[0])

TypeError: int() argument must be a string, a bytes-like object or a number, not 'Tensor'

Some answer says to remove tensor from dict but I don't know exactly ohw to remove them from dictionary if it is to be removed from there, and try downgrading or upgrading tensorflow. On commenting line 14 and using line 16 after uncommenting it gives error None is not subscriptable. I have also changed tf.gfile to tf.io.gfile . I am using tensorflow version 1.15.0 after downgrading.

CodePudding user response：

About the first error: You probably using the following code from the blog-post you mentioned:

def load_model(model_name):
  base_url = 'http://download.tensorflow.org/models/object_detection/'
  model_file = model_name   '.tar.gz'
  model_dir = tf.keras.utils.get_file(
    fname=model_name, 
    origin=base_url   model_file,
    untar=True)
 
  model_dir = pathlib.Path(model_dir)/"saved_model"
 
  model = tf.saved_model.load(str(model_dir))
 
  return model

use a debugger to check if model is being downloaded from the url.

About the second error:

output_dict = run_inference_for_single_image(model, image_np)

seems to return a dictionary with tensors as values.

Try:

num_detections = int(output_dict.pop('num_detections').numpy())