Machine Learning University: Accelerated Computer Vision Class

Last update: Dec 28, 2022

Overview

Machine Learning University: Accelerated Computer Vision Class

This repository contains slides, notebooks, and datasets for the Machine Learning University (MLU) Computer Vision class. Our mission is to make Machine Learning accessible to everyone. We have courses available across many topics of machine learning and believe knowledge of ML can be a key enabler for success. This class is designed to help you get started with Computer Vision, learn about widely used Machine Learning techniques, and apply them to real-world problems.

YouTube

Watch all Computer Vision class video recordings in this YouTube playlist from our YouTube channel.

Course Overview

There are three lectures and one final project for this class.

Lecture 1	Lecture 2	Lecture 3
Intro to ML	Image Datasets	Advanced CNNs: VGGNet and ResNet
Intro to Computer Vision	Training Neural Networks	Object Detection
Neural Networks	Modern CNNs: LeNet and AlexNet	Semantic Segmentation
Convolutional Neural Networks	Model fine-tuning

Final Project: Practice working with a "real-world" computer vision dataset for the final project. Final project dataset is in the data/final_project_dataset folder. For more details on the final project, check out this notebook.

Contribute

If you would like to contribute to the project, see CONTRIBUTING for more information.

License

The license for this repository depends on the section. Data set for the course is being provided to you by permission of Amazon and is subject to the terms of the Amazon License and Access. You are expressly prohibited from copying, modifying, selling, exporting or using this data set in any way other than for the purpose of completing this course. The lecture slides are released under the CC-BY-SA-4.0 License. The code examples are released under the MIT-0 License. See each section's LICENSE file for details.

Machine Learning University: Accelerated Computer Vision Class

Related tags

Overview

Machine Learning University: Accelerated Computer Vision Class

YouTube

Course Overview

Contribute

License

Owner

AWS Samples

Code for visualizing the loss landscape of neural nets

Detectorch - detectron for PyTorch

Learning Versatile Neural Architectures by Propagating Network Codes

Tensorflow implementation of Swin Transformer model.

deep learning for image processing including classification and object-detection etc.

VGGVox models for Speaker Identification and Verification trained on the VoxCeleb (1 & 2) datasets

Tensorflow implementation of "Learning Deep Features for Discriminative Localization"

Deep Learning Datasets Maker is a QGIS plugin to make datasets creation easier for raster and vector data.

RoIAlign & crop_and_resize for PyTorch

Official PyTorch code for "BAM: Bottleneck Attention Module (BMVC2018)" and "CBAM: Convolutional Block Attention Module (ECCV2018)"

ICRA 2021 "Towards Precise and Efficient Image Guided Depth Completion"

Code for the ICCV2021 paper "Personalized Image Semantic Segmentation"

Implementations for the ICLR-2021 paper: SEED: Self-supervised Distillation For Visual Representation.

Code for Towards Unifying Behavioral and Response Diversity for Open-ended Learning in Zero-sum Games

This repository contains the code and models necessary to replicate the results of paper: How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective

Code for AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Network (ICCV 2021).

[ ICCV 2021 Oral ] Our method can estimate camera poses and neural radiance fields jointly when the cameras are initialized at random poses in complex scenarios (outside-in scenes, even with less texture or intense noise )

Stacked Recurrent Hourglass Network for Stereo Matching

This is the official code of our paper "Diversity-based Trajectory and Goal Selection with Hindsight Experience Relay" (PRICAI 2021)

Saliency - Framework-agnostic implementation for state-of-the-art saliency methods (XRAI, BlurIG, SmoothGrad, and more).