Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

Commit b481adc

Browse files
added script to work with images
1 parent 397eb59 commit b481adc

File tree

1 file changed

+127
-0
lines changed

1 file changed

+127
-0
lines changed

‎detect_from_image.py

Lines changed: 127 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,127 @@
1+
import numpy as np
2+
import argparse
3+
import os
4+
import tensorflow as tf
5+
import matplotlib.pyplot as plt
6+
import pathlib
7+
8+
from object_detection.utils import ops as utils_ops
9+
from object_detection.utils import label_map_util
10+
from object_detection.utils import visualization_utils as vis_util
11+
12+
# patch tf1 into `utils.ops`
13+
utils_ops.tf = tf.compat.v1
14+
15+
# Patch the location of gfile
16+
tf.gfile = tf.io.gfile
17+
18+
19+
def load_model(model_path):
20+
model = tf.saved_model.load(model_path)
21+
return model
22+
23+
24+
25+
def load_image_into_numpy_array(path):
26+
"""Load an image from file into a numpy array.
27+
28+
Puts image into numpy array to feed into tensorflow graph.
29+
Note that by convention we put it into a numpy array with shape
30+
(height, width, channels), where channels=3 for RGB.
31+
32+
Args:
33+
path: a file path (this can be local or on colossus)
34+
35+
Returns:
36+
uint8 numpy array with shape (img_height, img_width, 3)
37+
"""
38+
img_data = tf.io.gfile.GFile(path, 'rb').read()
39+
image = Image.open(BytesIO(img_data))
40+
(im_width, im_height) = image.size
41+
return np.array(image.getdata()).reshape(
42+
(im_height, im_width, 3)).astype(np.uint8)
43+
44+
45+
def run_inference_for_single_image(model, image):
46+
# The input needs to be a tensor, convert it using `tf.convert_to_tensor`.
47+
input_tensor = tf.convert_to_tensor(image)
48+
# The model expects a batch of images, so add an axis with `tf.newaxis`.
49+
input_tensor = input_tensor[tf.newaxis,...]
50+
51+
# Run inference
52+
output_dict = model(input_tensor)
53+
54+
# All outputs are batches tensors.
55+
# Convert to numpy arrays, and take index [0] to remove the batch dimension.
56+
# We're only interested in the first num_detections.
57+
num_detections = int(output_dict.pop('num_detections'))
58+
output_dict = {key: value[0, :num_detections].numpy()
59+
for key, value in output_dict.items()}
60+
output_dict['num_detections'] = num_detections
61+
62+
# detection_classes should be ints.
63+
output_dict['detection_classes'] = output_dict['detection_classes'].astype(np.int64)
64+
65+
# Handle models with masks:
66+
if 'detection_masks' in output_dict:
67+
# Reframe the the bbox mask to the image size.
68+
detection_masks_reframed = utils_ops.reframe_box_masks_to_image_masks(
69+
output_dict['detection_masks'], output_dict['detection_boxes'],
70+
image.shape[0], image.shape[1])
71+
detection_masks_reframed = tf.cast(detection_masks_reframed > 0.5, tf.uint8)
72+
output_dict['detection_masks_reframed'] = detection_masks_reframed.numpy()
73+
74+
return output_dict
75+
76+
77+
def run_inference(model, category_index, image_path):
78+
if os.path.isdir(image_path):
79+
image_paths = []
80+
for file_extension in ('*.png', '*jpg'):
81+
image_paths.extend(glob.glob(os.path.join(image_path, file_extension)))
82+
83+
for i_path in image_paths:
84+
image_np = load_image_into_numpy_array(i_path)
85+
# Actual detection.
86+
output_dict = run_inference_for_single_image(model, image_np)
87+
# Visualization of the results of a detection.
88+
vis_util.visualize_boxes_and_labels_on_image_array(
89+
image_np,
90+
output_dict['detection_boxes'],
91+
output_dict['detection_classes'],
92+
output_dict['detection_scores'],
93+
category_index,
94+
instance_masks=output_dict.get('detection_masks_reframed', None),
95+
use_normalized_coordinates=True,
96+
line_thickness=8)
97+
plt.imshow(image_np)
98+
plt.show()
99+
elif
100+
image_np = load_image_into_numpy_array(image_path)
101+
# Actual detection.
102+
output_dict = run_inference_for_single_image(model, image_np)
103+
# Visualization of the results of a detection.
104+
vis_util.visualize_boxes_and_labels_on_image_array(
105+
image_np,
106+
output_dict['detection_boxes'],
107+
output_dict['detection_classes'],
108+
output_dict['detection_scores'],
109+
category_index,
110+
instance_masks=output_dict.get('detection_masks_reframed', None),
111+
use_normalized_coordinates=True,
112+
line_thickness=8)
113+
plt.imshow(image_np)
114+
plt.show()
115+
116+
117+
if __name__ == '__main__':
118+
parser = argparse.ArgumentParser(description='Detect objects inside webcam videostream')
119+
parser.add_argument('-m', '--model', type=str, required=True, help='Model Path')
120+
parser.add_argument('-l', '--labelmap', type=str, required=True, help='Path to Labelmap')
121+
parser.add_argument('-i', '--image_path', type=str, required=True, help='Path to image (or folder)')
122+
args = parser.parse_args()
123+
124+
detection_model = load_model(args.model)
125+
category_index = label_map_util.create_category_index_from_labelmap(args.labelmap, use_display_name=True)
126+
127+
run_inference(detection_model, category_index, args.image_path)

0 commit comments

Comments
(0)

AltStyle によって変換されたページ (->オリジナル) /