Tensorflow object detection API tutorial error

问题

After struggling with compatibility issues between Tensorflow 2.00 and the object detection API, I downgraded to Tensorflow 1.15 to be able to train my own model. after completing the training I modified the jupyter notebook included in the Tensorflow object detection API repo to test on my own images but I keep getting this error:

Traceback (most recent call last): File "object_detection_tutorial_converted.py", line 254, in <module> show_inference(detection_model, image_path) File "object_detection_tutorial_converted.py", line 235, in show_inference output_dict = run_inference_for_single_image(model, image_np) File "object_detection_tutorial_converted.py", line 203, in run_inference_for_single_image num_detections = int(output_dict.pop('num_detections')) TypeError: int() argument must be a string, a bytes-like object or a number, not 'Tensor'

Here's my modified jupyter notebook

import os
import pathlib
import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile

from collections import defaultdict
from io import StringIO
from matplotlib import pyplot as plt
from PIL import Image
from IPython.display import display
from object_detection.utils import ops as utils_ops
from object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_util


# patch tf1 into `utils.ops`
utils_ops.tf = tf.compat.v1

# Patch the location of gfile
tf.gfile = tf.io.gfile


def load_model(model_name):
  model_dir = pathlib.Path(model_name)/"saved_model"
  model = model = tf.compat.v2.saved_model.load(str(model_dir), None)
  model = model.signatures['serving_default']
  return model


# List of the strings that is used to add correct label for each box.
PATH_TO_LABELS = 'training/label_map.pbtxt'
category_index = label_map_util.create_category_index_from_labelmap(PATH_TO_LABELS, use_display_name=True)


TEST_IMAGE_PATHS.
PATH_TO_TEST_IMAGES_DIR = pathlib.Path('test_images')
TEST_IMAGE_PATHS = sorted(list(PATH_TO_TEST_IMAGES_DIR.glob("*.jpg")))
TEST_IMAGE_PATHS



model_name = 'devices_graph'
detection_model = load_model(model_name)


print(detection_model.inputs)


detection_model.output_dtypes


detection_model.output_shapes


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


# Run it on each test image and show the results:


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)

  display(Image.fromarray(image_np))



for image_path in TEST_IMAGE_PATHS:
  show_inference(detection_model, image_path)

回答1:

First you need to create an inference of the model using the script in the below link and later load the "frozen_inference_graph.pb" file/model, We need to give full path not just the folder path.

https://github.com/tensorflow/models/blob/master/research/object_detection/export_inference_graph.py

example path MODEL_PATH = '/home/sumanh/tf_models/Archive/model/ssd_inception_v2_coco_2018_01_28/190719/frozen_inference_graph.pb'

回答2:

That's strange this worked for tensorflow 2.0.0 for me. Can you send console log

来源：https://stackoverflow.com/questions/59234718/tensorflow-object-detection-api-tutorial-error

标签

tensorflow

machine-learning

object-detection

object-detection-api