mlwscv2002

Welcome to the Duke Machine Learning Winter School: Computer Vision 2022!

The MLWS-CV includes 3 hands-on training sessions on implementing machine learning tools with the PyTorch software platform. You can see the full description at https://plus.datascience.duke.edu/mlwscv2022

Day 1: Introduction to PyTorch (Billy Carson)

Student notebook (contains space for student to code along): https://github.com/dukeplusds/mlwscv2022/blob/main/day1_student_notebook.ipynb
Full solutions notebook: https://github.com/dukeplusds/mlwscv2022/blob/main/day1_solution_notebook.ipynb

Day 2: Pytorch for image analysis with convolutional neural networks (Gavin Karr)

Student notebook (contains space for student to code along): https://github.com/dukeplusds/mlwscv2022/blob/main/day2_student_notebook.ipynb
Full solutions notebook: https://github.com/dukeplusds/mlwscv2022/blob/main/day2_solution_notebook.ipynb

Day 3: PyTorch for image analysis including image segmentation and object detection (Akhil Ambekar)

Part 1:
Student notebook (contains space for student to code along): https://github.com/dukeplusds/mlwscv2022/blob/main/day3_student_notebook_part1.ipynb
Full solutions notebook: https://github.com/dukeplusds/mlwscv2022/blob/main/day3_solutions_notebook_part1.ipynb

Part 2:
Student notebook (contains space for student to code along): https://github.com/dukeplusds/mlwscv2022/blob/main/day3_student_notebook_part2.ipynb
Full solutions notebook: https://github.com/dukeplusds/mlwscv2022/blob/main/day3_solutions_notebook_part2.ipynb

We are using a virtual computing environment provided by Duke's Office of Information Technology (OIT). For those that are interested, the source code for the Docker container can be found here: https://gitlab.oit.duke.edu/mccahill/ml-winter-school

Duke Machine Learning Winter School: Computer Vision 2022

Related tags

Overview

mlwscv2002

Owner

Duke + Data Science (+DS)

Raster Vision is an open source Python framework for building computer vision models on satellite, aerial, and other large imagery sets

Code for our method RePRI for Few-Shot Segmentation. Paper at http://arxiv.org/abs/2012.06166

FAST Aiming at the problems of cumbersome steps and slow download speed of GNSS data

Controlling Hill Climb Racing with Hand Tacking

Towards Debiasing NLU Models from Unknown Biases

My implementation of transformers related papers for computer vision in pytorch

[EMNLP 2021] Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training

Simple converter for deploying Stable-Baselines3 model to TFLite and/or Coral

SparseML is a libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models

Predicting path with preference based on user demonstration using Maximum Entropy Deep Inverse Reinforcement Learning in a continuous environment

Official Code for AdvRush: Searching for Adversarially Robust Neural Architectures (ICCV '21)

Multi-task Self-supervised Object Detection via Recycling of Bounding Box Annotations (CVPR, 2019)

PyTorch implementation of an end-to-end Handwritten Text Recognition (HTR) system based on attention encoder-decoder networks

Convert dog pictures into various painting styles. Try LimnPet

Time series annotation library.

The official TensorFlow implementation of the paper Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition

A criticism of a recent paper on buggy image downsampling methods in popular image processing and deep learning libraries.

RaceBERT -- A transformer based model to predict race and ethnicty from names

Neural Cellular Automata + CLIP

Annealed Flow Transport Monte Carlo