Thomas Simonini's Projects
A CNN that make facial keypoint detection and real time filtering
Recurrent Neural Network that translates English to French
A curated list of awesome AI tools for game developers
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
[Work in Progress] ICM plugin for OpenAI Baselines
A better default template for Unity WebGL
Public repo for HF blog posts
A DCGAN that generate Cat pictures 🐱💻
A simple cifar-10 classifier with PyTorch
Convolutional Neural Networks
Public repository for DSS plugins
A DQL implementation with keras
Implementations from the free course Deep Reinforcement Learning with Tensorflow and PyTorch
A set of Deep Reinforcement Learning Agents implemented in Tensorflow.
Some DGAN (Deep Generative Adversarial Networks) implementations to generate human faces
A Generative Adversarial Network that generate human faces
Deep Learning Foundations Nanodegree. Udacity Project 1: Your first neural network
An RNN that generates new scripts for the Simpsons' tv show
In this project, you'll classify images from the CIFAR-10 dataset. The dataset consists of airplanes, dogs, cats, and other objects. The dataset will need to be preprocessed, then train a convolutional neural network on all the samples. You'll normalize the images, one-hot encode the labels, build a convolutional layer, max pool layer, and fully connected layer. At then end, you'll see their predictions on the sample images.
A Seq-to-seq model that translates English to French
Built a deep neural network that functions as part of an end-to-end automatic speech recognition (ASR) pipeline.
Convolutional Neural Network that recognizes dog breeds
An OpenAI Gym environment for the Flappy Bird game
Some GAN (Generative Adversarial Networks) implementations to generate MNIST images
A toolkit for developing and comparing reinforcement learning algorithms.
OpenAI gym environment for donkeycar simulator
A gym version of various games for reinforcenment learning.
Additional code for Stable-baselines3 to load and upload models from the Hub.