Deep Learning, NLP, NMT, AI, ML
A 🤗 Datasets extension package that provides support for executing arbitrary SQL queries on HF datasets. It uses DuckDB as a SQL engine and follows its query syntax. Installation Quick Start
Read more
Did you manage to spill samples from your train set to your test set? from did_it_spill import check_spill spills = check_spill(train_loader, test_loader) print(f”You have {len(spills)} spills in your test set!”) The library computes hashes of your data to determine if you have samples spilled over from your train set to test set. Currently only for PyTorch. Installation Outputs Function outputs a list of tuples. Each tuple corresponds to a leak. The first index is where in the first loader the […]
Read more
Python scripts for performing 6D pose estimation and shape reconstruction using the CenterSnap model in ONNX The original model has not been officially released, therefore, there might be changes to the official model later on. The examples seem to not properly work when using a camera other than the one in the original dataset. This is probably due to an implementation mistake on this repository, if you find the issue, please submit an issue or PR. The model only works […]
Read more
This repo contains the supported code and configuration files to reproduce semantic segmentaion results of TransDA. Paper Smoothing Matters: Momentum Transformer for Domain Adaptive Semantic Segmentation Abstract After the great success of Vision Transformer variants (ViTs) in computer vision, it has also demonstrated great potential in domain adaptive semantic segmentation. Unfortunately, straightforwardly applying local ViTs in domain adaptive semantic segmentation does not bring in expected improvement. We find that the pitfall of local ViTs is due to the severe high-frequency […]
Read more
Convert ISOs and archives into CD CHD for emulation. If you use RetroArch or possibly any emulator that supports CHD files, then you might want to convert your ISO and CUE+BIN files to it. It is a compressed single file format. The helper tool chdman from the MAME tools can do that. And often the files are in archives, so they need to be extracted first in a temporary folder, which 7z does. No need for manual extraction, this script […]
Read more
Practice exercises in pattern recognition, ideal for beginner and intermediate programmers. This uses the patterns at https://www.visualpatterns.org/ by Fawn Nguyen. The site and this module are licensed under a Creative Commons Attribution license. The patterns are not in order of difficulty. Many are simple, some are incredibly hard. THIS MODULE IS CURRENTLY UNDER CONSTRUCTION AND NOT WORKING YET. Installation To install with pip, from the Command Prompt/terminal run: python -m pip install programmedpatterns Contribute Currently a lot of basic programming […]
Read more
FREE Reverse Engineering Self-Study Course HERE A traffic generator pentesting tool to generate random traffic with random mac and ip addresses in addition to random sequence numbers to a particular ip and port. pip3 install scapy chmod +x traffic-generator sudo ./traffic-generator 127.0.0.1 80 1000 Terms Of Use Do NOT use this on any computer you do not own or are not allowed to run this on. You may NEVER attempt to sell this, it is free and open source. The […]
Read moreIn the previous Python Basics video course, you set up Python on your computer. With Python installed, you’re ready ready to start coding! In this video course, you’ll: Write your first Python program Learn what happens when you run a program with an error Learn how to declare a variable and inspect its value Learn how to write comments This course can be enjoyed alone or as an accompaniment to Python Basics: A Practical Introduction to Python 3. Ready to […]
Read moreCloud computing is powering a new age of data and AI by democratizing access to scalable compute, storage, and networking infrastructure and services. Thanks to the cloud, organizations can now collect data at an unprecedented scale and use it to train complex models and generate insights.  While this increasing demand for data has unlocked new possibilities, it also raises concerns about privacy and security, especially in regulated industries such as
Read moreTranslator, a Microsoft Azure Cognitive Service, is adopting Z-code Mixture of Experts models, a breakthrough AI technology that significantly improves the quality of production translation models. As a component of Microsoft’s larger XYZ-code initiative to combine AI models for text, vision, audio, and language, Z-code supports the creation of AI systems that can speak, see, hear, and understand. This effort is a part of Azure AI and Project Turing, focusing on building multilingual, large-scale language models that support various production […]
Read more