martinengelcke

models

Models and examples built with TensorFlow

google-research

Google Research

pytorch-image-models

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

Yet-Another-EfficientDet-Pytorch

The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.

datasets

TFDS is a collection of datasets ready to use with TensorFlow, Jax, ...

sacred

Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.

pytorch-optimizer

torch-optimizer -- collection of optimizers for Pytorch

ResNeXt

Implementation of a classification framework from the paper Aggregated Residual Transformations for Deep Neural Networks

neural_renderer

A PyTorch port of the Neural 3D Mesh Renderer

resnet-1k-layers

Deep Residual Networks with 1K Layers

tfrecord

Standalone TFRecord reader/writer with PyTorch data loaders

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)

test-tube

Python library to easily log experiments and parallelize hyperparameter search for neural networks

DeepV2D

torchlayers

Shape and dimension inference (Keras-like) for PyTorch layers and neural networks

video_prediction

Stochastic Adversarial Video Prediction

unsupervised_detection

An Unsupervised Learning Framework for Moving Object Detection From Videos

flowpp

Code for reproducing Flow ++ experiments

MABN

OxThesis

LaTeX template for an Oxford University thesis

pixelobjectness

Generic Foreground Segmentation in Images

genesis

Official PyTorch implementation of GENESIS and GENESIS-V2

biva-pytorch

Official PyTorch BIVA implementation (BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modeling)

SCALOR

Official Release of ICLR 2020 paper "SCALOR: Generative World Models with Scalable Object Representations"

flowplusplus

Implementation of Flow++ in PyTorch

improved_vrnn

Code for Improved Condtional VRNNs for Video Prediction

cophy

"CoPhy: Counterfactual Learning of Physical Dynamics", F. Baradel, N. Neverova, J. Mille, G. Mori, C. Wolf, ICLR'2020

BIVA

BIVA: A Very Deep Hierarchy of Latent Variables forGenerative Modeling

proVLAE

nyu-depth-v2-tools

Tools used in [2] to pre-process the ground truth segmentations to evaluate superpixel algorithms.