Tensorflow 对象检测 API 教程错误

Question

在努力解决 Tensorflow 2.00 和对象检测 API 之间的兼容性问题后，我降级到 Tensorflow 1.15，以便能够训练我自己的模型。完成培训后，我修改了Tensorflow object detection API中包含的jupyter笔记本存储库来测试我自己的图像，但我不断收到此错误:

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'

这是我修改后的 jupyter 笔记本

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)

Answer 1

首先，您需要使用以下链接中的脚本创建模型的推理，然后加载“frozen_inference_graph.pb”文件/模型，我们需要提供完整路径而不仅仅是文件夹路径。

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

示例路径MODEL_PATH = '/home/sumanh/tf_models/Archive/model/ssd_inception_v2_coco_2018_01_28/190719/frozen_inference_graph.pb'