thaonguyen19

faceswap

Deepfakes Software For All

fastai

The fastai deep learning library

Mask_RCNN

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

shap

A game theoretic approach to explain the output of any machine learning model.

vision_transformer

lucid

A collection of infrastructure and tools for research in neural network interpretability.

StarSpace

Learning embeddings for classification, retrieval and ranking.

scenic

Scenic: A Jax Library for Computer Vision Research and Beyond

FaceForensics

Github of the FaceForensics dataset

Klayers

Python Packages as AWS Lambda Layers

texture-vs-shape

Pre-trained models, data, code & materials from the paper "ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness" (ICLR 2019 Oral)

ImageNet

This implements training of popular model architectures, such as AlexNet, ResNet and VGG on the ImageNet dataset(Now we supported alexnet, vgg, resnet, squeezenet, densenet)

flaxmodels

Pretrained deep learning models for Jax/Flax: StyleGAN2, GPT2, VGG, ResNet, etc.

intrinsic-dimension

cvpr18-inaturalist-transfer

Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning. CVPR 2018

change-detection-tutorial

Tutorial on change detection in time series data

tf_classification

Training, evaluation and testing code for image classification using TensorFlow

learning-not-to-learn

[CVPR2019]Learning Not to Learn : An adversarial method to train deep neural networks with biased data

nnet-survival

Discrete-Time Survival Model for Neural Networks

sortpool2d

A new kind of pooling layer for faster and sharper convergence

goldfinch

Privacy-AdversarialLearning

[ECCV 2018] Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study

cs375

Course Repository for CS 375 (Large Scale Neural Network Modules for Neuroscience)

papers

Papers for Summer 2018

differential-privacy-vs-fairness

Code for "Differential Privacy Has Disparate Impact on Model Accuracy" NeurIPS'19

tensorflow-models

Models built with TensorFlow

Low-Resolution-Face-Recognition

PLD-Accountant

Code for computing tight guarantees for differential privacy

dl4cv_team50

Final project for the course Deep Learning for Computer Vision at TUM. Contributors: Amir Biran, Victor Aliende Da Matta, Giorgio Fabbro, Magnus Lindström, Paolo Notaro

coinstac-dpsvm

COINSTAC code for Differentially Private Support Vector Machines (dpSVM)