CenterNet implementation by Tensorflow 2
Project description
tf-centernet
CenterNet implementation with Tensorflow 2.
Install
# Not yet uploaded.
# pip instal tf-centernet
Example
CenterNet object detection
import numpy as np
import PIL.Image
import centernet
# Default: num_classes=80
obj = centernet.ObjectDetection(num_classes=80)
# Default: weights_path=None
# num_classes=80 and weights_path=None: Pre-trained COCO model will be loaded.
# Otherwise: User-defined weight file will be loaded.
obj.load_weights(weights_path=None)
img = np.array(PIL.Image.open('./data/sf.jpg'))[..., ::-1]
# The image with predicted bounding-boxes is created if `debug=True`
boxes, classes, scores = obj.predict(img, debug=True)
TODO
- Object detection
- Pre-trained model for object detection
- Pose estimation
- Pre-trained model for pose estimation
- Training function and Loss definition
- Training data augmentation
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
tf-centernet-1.0.0.tar.gz
(6.2 kB
view hashes)
Built Distribution
Close
Hashes for tf_centernet-1.0.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 3d1df92eca7222427d64dba3f31733be1263f9f2b389a5fc6b5382908aeb0c71 |
|
MD5 | 70abfa697e3e44806fbbcffc136daf78 |
|
BLAKE2b-256 | 3aabb86fdca3d86c378b4da8d4c795ed4a0d4027dc0b49a0329c9488ea17750a |