nfnets

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

NFNets and Adaptive Gradient Clipping for SGD implemented in PyTorch. Find explanation at tourdeml.github.io/blog/

Pre-trained NFNets with 99% of the accuracy of the official paper "High-Performance Large-Scale Image Recognition Without Normalization".

This repo deals with a Kaggle competition: Shopee - Price Match Guarantee. The purpose is to determine if two products are the same by their images.

Pre-trained NFNets with 99% of the accuracy of the official paper "High-Performance Large-Scale Image Recognition Without Normalization".

Silver Medal Solution for Shopee - Price Match Guarantee competition on Kaggle

E-Commerce Product Matching using Deep Neural Networks

Signal Propagation Plot (SPP) library

Railway infrastructure segmentation with Pyramid Attention Network - prizewinner of Digital Breakthrough 2022 Hackathon

Presentation on Normalizer-Free (Res)Nets conducted at Wrocław University of Science and Technology on 10 March. 2021.

This is a warehouse for NFNets-pytorch-model, can be used to train your image dataset.