Stars
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Models and examples built with TensorFlow
A toolkit for developing and comparing reinforcement learning algorithms.
Graph Neural Network Library for PyTorch
Theano was a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It is being continued as PyTensor: www.github.…
TensorFlow-based neural network library
Python Script to download hundreds of images from 'Google Images'. It is a ready-to-run code!
BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)
Implementation of Graph Convolutional Networks in TensorFlow
NeuralTalk is a Python+numpy project for learning Multimodal Recurrent Neural Networks that describe images with sentences.
Google Cloud Client Library for Python
Starter code for working with the YouTube-8M dataset.
The Places365-CNNs for Scene Classification
Minimal, clean example of lstm neural network training in python, for learning purposes.
Shared repository for open-sourced projects from the Google AI Language team.
Pytorch implementation of Diffusion Models (https://arxiv.org/pdf/2006.11239.pdf)
Simple script for downloading Youtube comments without using the Youtube API
Theano-based implementation of Deep Q-learning
Research code for ECCV 2020 paper "UNITER: UNiversal Image-TExt Representation Learning"
[ECCV 2018] Official code for "Graph R-CNN for Scene Graph Generation"
Models of SEIRS epidemic dynamics with extensions, including network-structured populations, testing, contact tracing, and social distancing.
A collection of generative methods implemented with TensorFlow (Deep Convolutional Generative Adversarial Networks (DCGAN), Variational Autoencoder (VAE) and DRAW: A Recurrent Neural Network For Im…
A python toolkit for parsing captions (in natural language) into scene graphs (as symbolic representations).
C3D is a modified version of BVLC tensorflow to support 3D ConvNets.
[ECCV2020] A super-resolution dataset of paired LR-HR scene text images