Fast Image Retrieval (FIRe) is an open source project to promote image retrieval research. It implements most of the major binary hashing methods to date, together with different popular backbone networks and public datasets.

This project partially embodies the state-of-the-art practices in speaker verification technology up until 2020, while attaining the state-of-the-art performance on the VoxCeleb1 test sets.

Unofficial implementation of DualPatchNorm using tensorflow2. Include ablation study code too.

[IJCAI 2020] This is an official code implementation for Deep Polarized Network for Supervised Learning of Accurate Binary Hashing Codes.

Towards Maximizing the Representation Gap between In-Domain & Out-of-Distribution Examples

here are some classic networks for image classification implement by pytorch

Dual Path Networks for Keras 2.0+

deep conv backone for image classification

Dual Path Networks in tensorflow

My implementaion of super-resolution based on dual-path networks. It can be used directly to reconstruct your low-resolution image to high-resolution. Also, you can use your dataset to train your networks

Caffe models (including classification, detection and segmentation) and deploy files for famouse networks