LSNet The location-sensitive visual recognition tasks, including object detection, instance segmentation, and human pose estimation, can be formulated into localizing an anchor point (in red) and a set of landmarks (in green). Our work aims to offer a unified framework for these tasks. Abstract Object detection, instance segmentation, and pose estimation are popular visual recognition tasks which require localizing the object by internal or boundary landmarks. This paper summarizes these tasks as location-sensitive visual recognition and proposes a unified solution […]

neural-blend-shapes This repository provides an end-to-end library for automatic character rigging, skinning, and blend shapes generation, as well as a visualization tool. It is based on our work Learning Skeletal Articulations with Neural Blend Shapes that is published in SIGGRAPH 2021. Prerequisites Our code has been tested on Ubuntu 18.04. Before starting, please configure your Anaconda environment by conda env create -f environment.yaml conda activate neural-blend-shapes Or you may install the following packages (and their dependencies) manually: pytorch 1.8 tensorboard […]

Anime2Sketch Anime2Sketch: A sketch extractor for illustration, anime art, manga By Xiaoyu Xiang Introduction The repository contains the testing codes and pretrained weights for Anime2Sketch. Anime2Sketch is a sketch extractor that works well on illustration, anime art, and manga. It is an application based on the paper “Adversarial Open Domain Adaption for Sketch-to-Photo Synthesis”. Prerequisites Get Started Installation Install the required packages: pip install -r requirements.txt Download Pretrained Weights Please download the weights from GoogleDrive, and put it into the […]

QuickAI QuickAI is a Python library that makes it extremely easy to experiment with state-of-the-art Machine Learning models. Motivation When I started to get into more advanced Machine Learning, I started to see how these famous neural networkarchitectures(such as EfficientNet), were doing amazing things. However, when I tried to implement these architecturesto problems that I wanted to solve, I realized that it was not super easy to implement and quickly experiment with thesearchitectures. That is where QuickAI came in. It […]

SmallPebble Minimal deep learning library written from scratch in Python, using NumPy/CuPy. SmallPebble is a minimal automatic differentiation and deep learning library written from scratch in Python, using NumPy/CuPy. The implementation is relatively small, and mainly in the file: smallpebble.py. To help understand it, check out this introduction to autodiff, which presents an autodiff framework that works in the same way as SmallPebble (except using scalars instead of NumPy arrays). SmallPebble’s raison d’etre is to be a simplified deep learning […]

DCL-PyTorch Pytorch implementation for the Dynamic Concept Learner (DCL). Prerequisites Python 3 PyTorch 1.0 or higher, with NVIDIA CUDA Support Other required python packages specified by requirements.txt. See the Installation. Installation Install Jacinle: Clone the package, and add the bin path to your global PATH environment variable: git clone https://github.com/vacancy/Jacinle –recursive export PATH=/bin:$PATH Clone this repository: git clone https://github.com/zfchenUnique/DCL-Release.git –recursive Create a conda environment for NS-CL, and install the requirements. This includes the required python packagesfrom both Jacinle NS-CL. Most […]

DeepMetaHandles is a shape deformation technique. It learns a set of meta-handles for each given shape. The disentangled meta-handles factorize all the plausible deformations of the shape, while each of them corresponds to an intuitive deformation direction. A new deformation can then be generated by the “linear combination” of the meta-handles. Although the approach is learned in an unsupervised manner, the learned meta-handles possess strong interpretability and consistency. Environment setup Create a conda environment by conda env create -f environment.yml. […]

DA2Lite DA2Lite (Deep Architecture to Lite) is a toolkit to compress and accelerate deep network models. Install git clone https://github.com/da2so/DA2Lite.git You will need a machine with a GPU and CUDA installed.Then, you prepare runtime environment: pip install -r requirements.txt Use Run main.py(DA2Lite) runs with two main configurations like as follows: CUDA_VISIBLE_DEVICES=0 python main.py –train_config_file=./configs/train/cifar10/cifar10/vgg16.yaml –compress_config_file=./configs/compress/tucker.yaml The first one is train_config_file, which indicates training configurations and the other is compress_config_file, which represents compress configurations.The details of available configurations are described in […]

torchsynth torchsynth is based upon traditional modular synthesis written in pytorch. It is GPU-optional and differentiable. Most synthesizers are fast in terms of latency. torchsynth is fast in terms of throughput. It synthesizes audio 16200x faster than realtime (714MHz) on a single GPU. This is of particular interest to audio ML researchers seeking large training corpora. Additionally, all synthesized audio is returned with the underlying latent parameters used for generating the corresponding audio. This is useful for multi-modal training regimes. […]

mbpo_pytorch This is a re-implementation of the model-based RL algorithm MBPO in pytorch as described in the following paper: When to Trust Your Model: Model-Based Policy Optimization. This code is based on a previous paper in the NeurIPS reproducibility challenge that reproduces the result with a tensorflow ensemble model but shows a significant drop in performance with a pytorch ensemble model. This code re-implements the ensemble dynamics model with pytorch and closes the gap. Reproduced results The comparison are done […]