Thomas Capelle's Projects
Exploring gradient chekcpoints resnets with fastai V2
This is a multi-channel implementation of ROCKET
A wandb SageMaker Studio Lab intro notebook
Solar segmentation of PV modules
A simple spaCy component for streamlit
Tensorflow port of the Stable Diffusion Model
Space-Time Attention Model
Stanford University Neural-network for Solar Electricity Trend
Minimal repo for sweep cap
A fastai based repo to ensemble image and tabular data.
My banner
my website
A simple wrapper to call openAI's chatGPT on the terminal written in Python
TensorFlow Metal Backend on Apple Silicon Experiments (just for fun)
TGS kagle challenge
Some example using Deep Learning for timeseries.
fastai V2 implementation of Timeseries classification papers.
A simple timeseries baseline with wandb
The official pytorch implementation of our paper "Is Space-Time Attention All You Need for Video Understanding?"
A simple Dataset generator for Moving Mnist
Exploring new PyTorch 1.11 data API
Implementation of Transformer model (originally from Attention is All You Need) applied to Time Series.
benchmarking some transformer deployments
Time series Timeseries Deep Learning Machine Learning Pytorch fastai | State-of-the-art Deep Learning library for Time Series and Sequences in Pytorch / fastai
The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."
A high-throughput and memory-efficient inference and serving engine for LLMs
Weights & Biases Addons is a repository consisting of additional unitilities and community contributions for supercharging your Weights & Biases workflows.