datature / discolight
discolight is a robust, flexible and infinitely hackable library for generating image augmentations ✨
☆25Updated 3 years ago
Related projects: ⓘ
- Semantic Segmentation using Tensorflow on popular Datasets like Ade20k, Camvid, Coco, PascalVoc☆69Updated last year
- Streamlit tool to explore coco datasets☆87Updated 2 years ago
- ☆162Updated 2 years ago
- Fast recipes for fastai☆11Updated last year
- Wheat Detection challenge on Kaggle☆83Updated 11 months ago
- Anchor optimization for RetinaNet.☆116Updated 4 years ago
- ☆123Updated last year
- ☆37Updated this week
- Helpers for detectron2☆40Updated 4 years ago
- IceData: Datasets Hub for the *IceVision* Framework☆49Updated 2 years ago
- AutoML for image augmentation. AutoAlbument uses the Faster AutoAugment algorithm to find optimal augmentation policies. Documentation - …☆199Updated 3 years ago
- The service for the demonstration of transforms in Albumentations library☆105Updated 2 months ago
- Custom image data generator for TF Keras that supports the modern augmentation module albumentations☆86Updated 2 years ago
- Unofficial Colab on how to train DETR, the intelligent object detector, with your own dataset. DETR = Detection Transformer☆40Updated 4 years ago
- Keras Implementation of Unet with EfficientNet as encoder☆47Updated 2 years ago
- A Tensorflow implementation of the DETR object detection architecture.☆62Updated 3 years ago
- Extensions for the `fastai2` library in the form of data augmentations and inference utilities. Specific to computer vision models. Infer…☆48Updated last year
- 🐦 Quickly annotate data from the comfort of your Jupyter notebook☆61Updated 4 years ago
- Object Detection Metrics☆39Updated last year
- Python lib for remo - the app for annotations and images management in Computer Vision☆186Updated 3 years ago
- Helper for dealing with MS-COCO annotations☆92Updated 2 weeks ago
- EfficientNets in 3D variant for keras and TF.keras☆53Updated 2 years ago
- A deep-learning pipeline for segmentation of ambiguous microscopic images.☆56Updated 3 weeks ago
- Catalyst.Segmentation☆28Updated 3 years ago
- PyTorch Lightning based training of Semantic Segmentation models☆37Updated last year
- Team [Save the Prostate] - solution☆18Updated 3 years ago
- self defined efficientnetV2 according to official version. Including converted ImageNet/21K/21k-ft1k weights.☆77Updated 2 years ago
- ☆34Updated 4 years ago
- Additional functionality for use with fastai’s medical imaging module☆15Updated 2 years ago
- vizgradcam is the fastest way to visualize GradCAM with your Keras models.☆60Updated 2 years ago
- ☆70Updated 3 years ago