Official implementation of "Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network".
The Autonomous Learning Library: A PyTorch Library for Building Reinforcement Learning Agents.
Pytorch implementation of a StyleGAN encoder. Images to latent space representation.
ActionAI is a python library for training machine learning models to classify human action.
Unofficial implementation of the model architecture of Fast-SCNN. Real-time Semantic Segmentation and mobile friendly memory consumption.
Tools and resources for open translation services.
Neural Network Library written in Python and built on top of JAX, an open-source high-performance deep learning library.
PyTorch3d provides efficient, reusable components for 3D Computer Vision research with PyTorch.
An ML framework to accelerate research and its path to production.
Multi Model Server (MMS) is a flexible and easy to use tool for serving deep learning models trained using any ML/DL framework.
This repo is about face recognition and triplet loss. I trained that model with TensorFlow 2.0 and I used Casia-WebFace as dataset.
This projects extends pytorch/fairseq with Transformer-based image captioning models. It is still in an early stage, only baseline models are available at the moment.
Ganzo is a framework to implement, train and run different types of GANs, based on PyTorch.
It includes LSH attention, reversible network, and chunking. It has been validated with an auto-regressive task (enwik8).
PyTorch re-implementation of Real-time Scene Text Detection with Differentiable Binarization
IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CVPR 2019
DDSP is a library of differentiable versions of common DSP functions (such as synthesizers, waveshapers, and filters).
Python scripts to parse your Messenger, Hangouts, WhatsApp and Telegram chat logs into DataFrames.
This project is intended to showcase the usage of a Keras multi-output model to predict age, gender and ethnicity from a given persons face.
Once for All: Train One Network and Specialize it for Efficient Deployment.
Poetry helps you declare, manage and install dependencies of Python projects, ensuring you have the right stack everywhere.
Optuna is an automatic hyperparameter optimization software framework, particularly designed for machine learning.
Code, model and data of DeeperForensics-1.0 will be made publicly available here.
The lightweight PyTorch wrapper for ML researchers. Scale your models. Write less boilerplate
This repository lets you train neural networks models for performing end-to-end full-page handwriting recognition using the Apache MXNet deep learning frameworks on the IAM Dataset.