PyTorch

An implementation of shampoo, proposed in Shampoo

shampoo.pytorch An implementation of shampoo, proposed in Shampoo : Preconditioned Stochastic Tensor Optimization by Vineet Gupta, Tomer Koren and Yoram Singer. # Suppose the size of the tensor grad (i, j, k), # dim_id = 1 and dim = j grad = grad.transpose_(0, dim_id).contiguous() # (j, i, k) transposed_size = grad.size() grad = grad.view(dim, -1) # (j, i x k) grad_t = grad.t() # (i x k, j) precond.add_(grad @ grad_t) # (j, j) inv_precond.copy_(_matrix_power(state[precond, -1 / order)) # (j, […]

Read more
Images

PyTorch NIMA: Neural IMage Assessment

PyTorch NIMA: Neural IMage Assessment PyTorch implementation of Neural IMage Assessment by Hossein Talebi and Peyman Milanfar. You can learn more from this post at Google Research Blog. Installing Docker docker run -it truskovskiyk/nima:latest /bin/bash PYPI package (In Progress) pip install nima VirtualEnv git clone https://github.com/truskovskiyk/nima.pytorch.git cd nima.pytorch virtualenv -p python3.7 env source ./env/bin/activate Dataset The model was trained on the AVA (Aesthetic Visual Analysis) datasetYou can get it from hereHere are some examples of images with theire scores Pre-train […]

Read more
Python

Python’s ChainMap: Manage Multiple Contexts Effectively

Sometimes when you’re working with several different dictionaries, you need to group and manage them as a single one. In other situations, you can have multiple dictionaries representing different scopes or contexts and need to handle them as a single dictionary that allows you to access the underlying data following a given order or priority. In those cases, you can take advantage of Python’s ChainMap from the collections module. ChainMap groups multiple dictionaries and mappings in a single, updatable view […]

Read more
QUESTION ANSWERING

Baseline code for Korean open domain question answering

Open-Domain Question Answering(ODQA)는 다양한 주제에 대한 문서 집합으로부터 자연어 질의에 대한 답변을 찾아오는 task입니다. 이때 사용자 질의에 답변하기 위해 주어지는 지문이 따로 존재하지 않습니다. 따라서 사전에 구축되어있는 Knowledge Resource(본 글에서는 한국어 Wikipedia)에서 질문에 대답할 수 있는 문서를 찾는 과정이 필요합니다. VumBleBot은 ODQA 문제를 해결하기 위해 설계되었습니다. 질문에 관련된 문서를 찾아주는 Retriever, 관련된 문서를 읽고 간결한 답변을 내보내주는 Reader가 구현되어 있습니다. 이 두 단계를 거쳐 만들어진 VumBleBot은 어떤 어려운 질문을 던져도 척척 답변을 해주는 질의응답 시스템입니다. bookmark_tabs Wrap-up report에 모델, 실험 […]

Read more
Transformer

Keeping Your Eye on the Ball Trajectory Attention in Video Transformers with python

Motionformer This is an official pytorch implementation of paper Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers. In this repository, we provide PyTorch code for training and testing our proposed Motionformer model. Motionformer use proposed trajectory attention to achieve state-of-the-art results on several video action recognition benchmarks such as Kinetics-400 and Something-Something V2. If you find Motionformer useful in your research, please use the following BibTeX entry for citation. @misc{patrick2021keeping, title={Keeping Your Eye on the Ball: Trajectory […]

Read more
Deep Learning

Repository for publicly available deep learning models developed in Rosetta community

trRosetta2 This package contains deep learning models and related scripts used by Baker group in CASP14. Installation Linux/Mac clone the package git clone https://github.com/RosettaCommons/trRosetta2cd trRosetta2 create conda environment using one of the .yml files: casp14-baker-linux-cpu.yml, casp14-baker-linux-gpu.yml, casp14-baker-mac-cpu.yml conda env create -f casp14-baker-linux-gpu.ymlconda activate casp14-baker download network weights [1.1G] wget https://files.ipd.uw.edu/pub/trRosetta2/weights.tar.bz2tar xf weights.tar.bz2 download and install third-party software ./install_dependencies.sh download sequence and structure databases wget http://wwwuser.gwdg.de/~compbiol/uniclust/2020_06/UniRef30_2020_06_hhsuite.tar.gzmkdir -p UniRef30_2020_06tar xf UniRef30_2020_06_hhsuite.tar.gz -C ./UniRef30_2020_06 wget https://files.ipd.uw.edu/pub/trRosetta2/pdb100_2020Mar11.tar.gztar xf pdb100_2020Mar11.tar.gz Obtain a PyRosetta licence and […]

Read more
tensorflow

Build tensorflow keras model pipelines in a single line of code

deep_autoviml Build keras pipelines and models in a single line of code! Build tensorflow keras model pipelines in a single line of code. Created by Ram Seshadri. Collaborators welcome. Permission granted upon request. Motivation ✨ deep_autoviml is a powerful new deep learning library with a very simple design goal: ✨ Make it as easy as possible for novices and experts alike to experiment with and build tensorflow.keras preprocessing pipelines and models in as few lines of code as possible. Watch […]

Read more
Dataset

A Dataset of Python Challenges for AI Research

Python Programming Puzzles (P3) This repo contains a dataset of python programming puzzles which can be used to teach and evaluate an AI’s programming proficiency. We hope this dataset with grow rapidly, and it is already diverse in terms of problem difficult, domain, and algorithmic tools needed to solve the problems. Please propose a new puzzle or browse newly proposed puzzles or contribute through pull requests. To learn more about how well AI systems such as GPT-3 can solve these […]

Read more
Machine Learning

Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time

Semi Hand-Object Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time (CVPR 2021). Installation Quick Demo (update soon) Training and Evaluation on HO3D Dataset Preparation Download the MANO model files (mano_v1_2.zip) from MANO website.Unzip and put mano/models/MANO_RIGHT.pkl into assets/mano_models. Download the YCB-Objectsused in HO3D dataset. Put unzipped folder object_models under assets. The structure should look like this: Semi-Hand-Object/ assets/ mano_models/ MANO_RIGHT.pkl object_models/ 006_mustard_bottle/ points.xyz textured_simple.obj …… Download and unzip HO3D datasetto path you like, the unzipped path is referred as […]

Read more
Machine Learning

LaneAF: Robust Multi-Lane Detection with Affinity Fields

LaneAF LaneAF: Robust Multi-Lane Detection with Affinity Fields Installation Clone this repository Install Anaconda Create a virtual environment and install all dependencies: conda create -n laneaf pip python=3.6source activate laneafpip install numpy scipy matplotlib pillow scikit-learnpip install opencv-pythonpip install https://download.pytorch.org/whl/cu101/torch-1.7.0%2Bcu101-cp36-cp36m-linux_x86_64.whlpip install https://download.pytorch.org/whl/cu101/torchvision-0.8.1%2Bcu101-cp36-cp36m-linux_x86_64.whlsource deactivate You can alternately find your desired torch/torchvision wheel from here. Clone and make DCNv2: cd models/dlagit clone https://github.com/lbin/DCNv2.gitcd DCNv2./make.sh TuSimple The entire TuSimple dataset should be downloaded and organized as follows: └── TuSimple/ ├── clips/ | └── […]

Read more
1 … 553 554 555 556 557 … 945