InferenceOnTFObjectDetection

InferenceOnTFObjectDetection.py

import numpy as np
from PIL import Image
from google.colab.patches import cv2_imshow

def load_image_into_numpy_array(path):
    """Load an image from file into a numpy array.

    Puts image into numpy array to feed into tensorflow graph.
    Note that by convention we put it into a numpy array with shape
    (height, width, channels), where channels=3 for RGB.

    Args:
      path: the file path to the image

    Returns:
      uint8 numpy array with shape (img_height, img_width, 3)
    """
    return np.array(Image.open(path))

image_path = "PATH TO YOUR INFERENCE IMAGE"
print('Running inference for {}... '.format(image_path), end='')

image_np = load_image_into_numpy_array(image_path)

# Things to try:
# Flip horizontally
# image_np = np.fliplr(image_np).copy()

# Convert image to grayscale, (You could uncomment this to try and see how the model reacts to a grayscale image)
# image_np = np.tile(
#     np.mean(image_np, 2, keepdims=True), (1, 1, 3)).astype(np.uint8)

# The input needs to be a tensor, convert it using `tf.convert_to_tensor`.
input_tensor = tf.convert_to_tensor(image_np)
# The model expects a batch of images, so add an axis with `tf.newaxis`.
input_tensor = input_tensor[tf.newaxis, ...]

detections = detect_fn(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(detections.pop('num_detections'))
detections = {key: value[0, :num_detections].numpy()
              for key, value in detections.items()}
detections['num_detections'] = num_detections

# detection_classes should be ints.
detections['detection_classes'] = detections['detection_classes'].astype(np.int64)

image_np_with_detections = image_np.copy()

viz_utils.visualize_boxes_and_labels_on_image_array(
      image_np_with_detections,
      detections['detection_boxes'],
      detections['detection_classes'],
      detections['detection_scores'],
      category_index,
      use_normalized_coordinates=True,
      max_boxes_to_draw=200,
      min_score_thresh=.4, # Adjust this value to set the minimum probability boxes to be classified as True
      agnostic_mode=False)

cv2_imshow(image_np_with_detections)

hi, I have a question about the saving model and loading model. the above code store as a checkpoint of the model can I load this model and save it in a different format like .h5 or .pb. it is possible or not I try a lot of code but nothing works correctly.