tfops-aug
tf-explain
tfops-aug | tf-explain | |
---|---|---|
1 | 1 | |
14 | 1,007 | |
- | 0.0% | |
4.9 | 0.0 | |
over 1 year ago | almost 2 years ago | |
Python | Python | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
tfops-aug
-
tfops-aug: Lightweight and fast image augmentation library based on TensorFlow Ops
With tfops-aug, you can easily apply an augmentation policy to your images, including shearing, translations, random gamma, random color shifts, solarization, posterization, histogram equalization, and more. The library is fully compatible with Tensorflow's data pipelines, so you can easily integrate it into your existing projects. And because it uses only Tensorflow operations, it's fast and efficient and can be directly applied on a tf.Tensor of type tf.uint8.
tf-explain
-
What alternative for explainable AI besides LIME do we have for deep learning models on images (keras)?
Have look at tf-explain and why not shap Shap?
What are some alternatives?
textaugment - TextAugment: Text Augmentation Library
CleanTF2plus - Clean TF2's sequel
tensorflow-yolov4-tflite - YOLOv4, YOLOv4-tiny, YOLOv3, YOLOv3-tiny Implemented in Tensorflow 2.0, Android. Convert YOLO v4 .weights tensorflow, tensorrt and tflite
horovod - Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.
yolov4-custom-functions - A Wide Range of Custom Functions for YOLOv4, YOLOv4-tiny, YOLOv3, and YOLOv3-tiny Implemented in TensorFlow, TFLite, and TensorRT.
jarconfig - combined scripts for tf2
mastercomfig - A modern customization framework for Team Fortress 2
pytest-visual - A visual testing framework for ML with automated change detection
seed_rl - SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.
nhcustom - nhcustom is a program whose purpose is to modify the Team Fortress 2 mod "no-hats-bgum".
Fast-SRGAN - A Fast Deep Learning Model to Upsample Low Resolution Videos to High Resolution at 30fps