Pinned Repositories
Black-box_Optimization_via_Deep_Generative-Exploratory_Networks
Deep neural networks have garnered tremendous excitement in recent years thanks to their superior learning capacity in the presence of abundant data resources. However, collecting an exhaustive dataset covering all possible scenarios is often slow, expensive, and even impractical. The goal of this project is to devise a new learning framework that can learn from a finite dataset and noisy feedback of data properties to discover novel samples of particular interest. We will design and implement algorithms to interweave emerging deep generative modeling with classical Markov decision processes. We will evaluate our method in comparison to existing approaches through extensive experiments, including but not limited to visual semantic extrapolation and natural adversarial examples in the context of autonomous vehicles.
image-recognition-groceries
Test machine learning power to classify product
recipes-telegram-bot
Generate and recommend recipes based on photos of your fridge
telegram-coffee-break
It's time to take a coffee break! your python code is running, and you'll be notified through telegram to see the progress of your code.
RomainGratier's Repositories
RomainGratier/recipes-telegram-bot
Generate and recommend recipes based on photos of your fridge
RomainGratier/Black-box_Optimization_via_Deep_Generative-Exploratory_Networks
Deep neural networks have garnered tremendous excitement in recent years thanks to their superior learning capacity in the presence of abundant data resources. However, collecting an exhaustive dataset covering all possible scenarios is often slow, expensive, and even impractical. The goal of this project is to devise a new learning framework that can learn from a finite dataset and noisy feedback of data properties to discover novel samples of particular interest. We will design and implement algorithms to interweave emerging deep generative modeling with classical Markov decision processes. We will evaluate our method in comparison to existing approaches through extensive experiments, including but not limited to visual semantic extrapolation and natural adversarial examples in the context of autonomous vehicles.
RomainGratier/telegram-coffee-break
It's time to take a coffee break! your python code is running, and you'll be notified through telegram to see the progress of your code.
RomainGratier/image-recognition-groceries
Test machine learning power to classify product
RomainGratier/datascience
Curated list of Python resources for data science.
RomainGratier/deepfrench
NLP French language model implementing ULMFiT
RomainGratier/gan_inpainting_for_pose_estimation
tackle pose estimation while occlusion appear with generative adversarial models
RomainGratier/gandissect
Pytorch-based tools for visualizing and understanding the neurons of a GAN. https://gandissect.csail.mit.edu/
RomainGratier/generative_inpainting
DeepFill v1/v2 with Contextual Attention and Gated Convolution, CVPR 2018, and ICCV 2019 Oral
RomainGratier/implicit
Fast Python Collaborative Filtering for Implicit Feedback Datasets
RomainGratier/recipe-app-api
RomainGratier/test-hierarchy-interactive
Created with CodeSandbox
RomainGratier/Vue.js-Tree-Data-Builder
Build data trees optimized for d3 structure quickly with this app!