NFNet Pytorch Implementation This repo contains pretrained NFNet models F0-F6 with high ImageNet accuracy from the paper High-Performance Large-Scale Image Recognition Without Normalization. The small models are as accurate as an EfficientNet-B7, but train 8.7 times faster. The large models set a new SOTA top-1 accuracy on ImageNet. NFNet F0 F1 F2 F3 F4 F5 F6+SAM Top-1 accuracy Brock et al. 83.6 84.7 85.1 85.7 85.9 86.0 86.5 Top-1 accuracy this implementation 82.82 84.63 84.90 85.46 85.66 85.62 TBD All […]

gymnastics A “gym” style toolkit for building lightweight Neural Architecture Search systems. I know, the name is awful. Installation Preferred option: Install from source: git clone [email protected]:jack-willturner/gymnastics.git cd gymnastics python setup.py install To install the latest release version: pip install gymnastics If you want to use NAS-Bench-101, follow the instructions here to get it set up. Overview Over the course of the final year of my PhD I worked a lot on Neural Architecture Search (NAS) and built a bunch […]

AECR-Net Contrastive Learning for Compact Single Image Dehazing, CVPR2021. Official Pytorch based implementation. Pytorch Version TODO: model code pretrained models MindSpore Version https://github.com/Booooooooooo/AECRNet-MindSpore by @wyb Performance GitHub https://github.com/GlassyWu/AECR-Net    

DeLighT: Very Deep and Light-weight Transformers This repository contains the source code of our work on building efficient sequence models: DeFINE (ICLR’20) and DeLighT (preprint). Overview In this repository, we share the source code of our paper DeLight, that delivers similar or better performance thantransformer-based models with significantly fewer parameters. DeLighT more efficiently allocates parameters both (1)within each Transformer block using DExTra, a deep and light-weight transformation and (2) across blocks usingblock-wise scaling, that allows for shallower and narrower DeLighT […]

XDVioDet Official implementation of “Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision” ECCV2020. The project website is XD-Violence. The features can be downloaded from our project website. where we oversample each video frame with the “5-crop” augment, “5-crop” means cropping images into the center and four corners. _0.npy is the center, _1~ _4.npy is the corners. How to train download or extract the features. use make_list.py in the list folder to generate the training and […]

chitra chitra (चित्र) is a Deep Learning library for Model Building, Explainable AI, Data Visualization, API Building & Deployment. Load Image from Internet url, filepath or numpy array and plot Bounding Boxes on the images easily. Model Training and Explainable AI. Easily create UI for Machine Learning models or Rest API backend that can be deployed for serving ML Models in Production. 📌 Highlights: [New] Framework Agnostic Model Serving & Interactive UI prototype app ✨🌟 [New] Data Visualization, Bounding Box […]

Lighting-the-Darkness-in-the-Deep-Learning-Era-Open This repository provides a unified online platform, LoLi-Platform http://mc.nankai.edu.cn/ll/, that covers many popular deep learning-based LLIE methods, of which the results can be produced through a user-friendly web interface, contains a low-light image and video dataset, LoLi-Phone https://drive.google.com/file/d/1QS4FgT5aTQNYy-eHZ_A89rLoZgx_iysR/view?usp=sharing, in which the images and videos are taken by various phones’ cameras under diverse illumination conditions and scenes, and collects deep learning-based low-light image and video enhancement methods, datasets, and evaluation metrics. More content and details can be found in our […]

Here is deepparse. Deepparse is a state-of-the-art library for parsing multinational street addresses using deep learning. Use deepparse to Use the pre-trained models to parse multinational addresses, retrain our pre-trained models on new data to parse multinational addresses, retrain our pre-trained models with your own prediction tags easily. Read the documentation at deepparse.org. Deepparse is compatible with the latest version of PyTorch and Python >= 3.7. Countries and Results We evaluate our models on two forms of address data clean […]

GIRAFFE This repository contains the code for the CVPR 2021 paper “GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields” GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields If you find our code or paper useful, please cite as @inproceedings{GIRAFFE, title = {GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields}, author = {Niemeyer, Michael and Geiger, Andreas}, booktitle = {Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)}, year = {2021} } TL; DR – Quick Start […]