Martin Engelcke's starred repositories
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.
pytorch-optimizer
torch-optimizer -- collection of optimizers for Pytorch
neural_renderer
A PyTorch port of the Neural 3D Mesh Renderer
resnet-1k-layers
Deep Residual Networks with 1K 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)
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
pixelobjectness
Generic Foreground Segmentation in Images
biva-pytorch
Official PyTorch BIVA implementation (BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modeling)
flowplusplus
Implementation of Flow++ in PyTorch
improved_vrnn
Code for Improved Condtional VRNNs for Video Prediction
nyu-depth-v2-tools
Tools used in [2] to pre-process the ground truth segmentations to evaluate superpixel algorithms.