PyTorch

Implementations of polygamma, lgamma, and beta functions for PyTorch

Implementations of polygamma, lgamma, and beta functions for PyTorch. It’s very hacky, but that’s usually ok for research use. To build, run: ./make.sh You’ll probably need to pass in the correct CUDA path to build.py, which is run inside make.sh, so modify it to instead call python build.py –cuda-path YOUR_CUDA_PATH Also, you’ll probably need to change the architecture version/CUDA compute capability inside make.sh, so replace sm_35 with whatever your GPU supports.Feel free to open an issue if you run into […]

Read more
Neural Network

Closing the generalization gap in large batch training of neural networks

Train longer, generalize better – Big batch training This is a code repository used to generate the results appearing in “Train longer, generalize better: closing the generalization gap in large batch training of neural networks” By Elad Hoffer, Itay Hubara and Daniel Soudry. It is based off convNet.pytorch with some helpful options such as: Training on several datasets Complete logging of trained experiment Graph visualization of the training/validation loss and accuracy Definition of preprocessing and optimization regime for each model […]

Read more
Natural Language Processing

Topic modeling on unstructured data in Space news articles retrieved

NLP Space News Topic Modeling topic modeling on unstructured data in Space news articles retrieved from the Guardian (UK) newspaper using API Project Idea Project Overview This project aims to learn topics published in Space news from the Guardian (UK) news publication. Motivation The model/tool would give an idea of what Space news topics matter to each publication over time. For example, a space mission led by the European Space Agency (ESA) might be more relevant/important to the Guardian than […]

Read more
Asyncio

Asynchronous and also synchronous non-official QvaPay client for asyncio and Python

QvaPay client for Python Asynchronous and also synchronous non-official QvaPay client for asyncio and Python language. This library is still under development, the interface could be changed. Features Response models with type hints annotated fully (Also internal code have type hints annotated fully) thank you to Python’s type hints (or annotations) and pydantic Asynchronous and synchronous behavior thank you to httpx Coverage 100% Project collaborative and open source GitHub https://github.com/leynier/aioqvapay    

Read more
Timer

A Toastmasters-inspired speech timer for online scrum meetings

Qolor Tyme This is a Toastmasters-inspired speech timer for use during online daily scrum meeting updates. It is based on PyQt, which is Python API for Qt (pronounced “cute”) cross-platform GUI framework, hence the name Qolor Tyme. I honestly don’t know why they called it PyQt instead of QtPy, which would have made it “cutie-pie” ¯_(ツ)_/¯ Installation Use pip: pip install qolor-tyme Running Run it as the package. It accepts an optional timeout interval (default is 90 seconds per Agile […]

Read more
API

An unofficial API of 1cak.com

1cak – is Indonesian web that provide lot of fun. Endpoint Lol -> 10 Recent stored posts on databaseExample: https://onecak.azurewebsites.net/?lol Shuffle -> Select random posts from databaseExample: https://onecak.herokuapp.com/?shuffle=5 Info This app is subject of experiment, you may found some weird thing or even useless code.If so, please ignore or do PR.Thanks. GitHub https://github.com/dickymuliafiqri/onecak    

Read more
PyTorch

Robust Video Matting (RVM) in PyTorch

Official repository for the paper Robust High-Resolution Video Matting with Temporal Guidance. RVM is specifically designed for robust human video matting. Unlike existing neural models that process frames as independent images, RVM uses a recurrent neural network to process videos with temporal memory. RVM can perform matting in real-time on any videos without additional inputs. It achieves 4K 76FPS and HD 104FPS on an Nvidia GTX 1080 Ti GPU. The project was developed at ByteDance Inc.

Read more
PyTorch

For something in between a pytorch and a karpathy/micrograd

tinygrad For something in between a pytorch and a karpathy/micrograd This may not be the best deep learning framework, but it is a deep learning framework. Due to its extreme simplicity, it aims to be the easiest framework to add new accelerators to, with support for both inference and training. Support the simple basic ops, and you get SOTA vision extra/efficientnet.py and language extra/transformer.py models. We are working on support for the Apple Neural Engine. Eventually, we will build custom […]

Read more
Debugger

Generate more helpful exception messages for numpy/pytorch matrix algebra expressions

See article Clarifying exceptions and visualizing tensor operations in deep learning code and TensorSensor implementation slides (PDF). One of the biggest challenges when writing code to implement deep learning networks, particularly for us newbies, is getting all of the tensor (matrix and vector) dimensions to line up properly. It’s really easy to lose track of tensor dimensionality in complicated expressions involving multiple tensors and tensor operations. Even when just feeding data into predefined Tensorflow network layers, we still need to […]

Read more
Deep Learning

An implementation of Performer, a linear attention-based transformer in Pytorch

Performer – Pytorch An implementation of Performer, a linear attention-based transformer variant with a Fast Attention Via positive Orthogonal Random features approach (FAVOR+). Install $ pip install performer-pytorch Then you must run the following, if you plan on training an autoregressive model $ pip install -r requirements.txt Usage Performer Language Model import torch from performer_pytorch import PerformerLM model = PerformerLM( num_tokens = 20000, max_seq_len = 2048, # max sequence length dim = 512, # dimension depth = 12, # layers […]

Read more
1 … 503 504 505 506 507 … 939