D

deep-learning

对不同尺寸的交通信号灯图片做红黄绿分类

In SupeRAuGAN we implement a novel data augmentation technique tailored to Generative Adversarial Networks in order to reduce discriminator overfitting and stabilize training

A very simple example of using RL in real life using servo motors.

Learn to drive an radio-controlled car using only a camera. Uses a DonkeyCar simulation, SAC and a VAE. By Winder Research.

Cat facial detection and landmark recognition in Python

A clean, modular implementation of Physics-Informed Neural Networks (PINNs) for solving the 1D and 2D wave equation using PyTorch.

Classifier to assign label to particle

3D Hand Pose Estimation using Multi-View CNNs

✭ MAGNETRON ™ ✭: Detectron2 is a platform for PROXIA that can do POSE ESTIMATION, object detection, segmentation and other visual recognition tasks.

Fine tunning of a deep neural network (using convolutionnal layers) to reconize a digit from a picture of an handwritten one.

Projet pédagogique en algorithmie et intelligence artificielle consistant à créer un agent (Kevin) capable de résoudre un labyrinthe.

Le projet explore plusieurs approches :

Génération de labyrinthes (DFS, Prim) Algorithmes de recherche de chemin (A*, Dijkstra) Apprentissage supervisé (Imitation Learning avec CNN) Apprentissage par renforcement (Deep Q-Network)

Des outils de visualisation permettent de générer des images et des GIFs montrant Kevin se déplacer dans le labyrinthe.

Projet réalisé dans le cadre de la formation Développeur en Intelligence Artificielle (Simplon).

A simplified version of "Cliffworld" in an OpenAI Gym Environment

An OpenAI Gym for Shopping Cart Reinforcement Learning.

CS 7643 — Spring 2019 Project

Goal: learn more about the underlying deep learning model of GPT2: the Transformer model and, more broadly, the attention mechanism.

Introduction to classification using machine learning and deep learning (PyTorch, TensorFlow, Keras)

BIL635 - Modified Version of "Finding a Target with Zero-shot Invariant and Efficient Visual Search" v2

BIL635 - Modified Version of "Finding a Target with Zero-shot Invariant and Efficient Visual Search"