LeViT This repository contains PyTorch evaluation code, training code and pretrained models for LeViT. They obtain competitive tradeoffs in terms of speed / precision: For details see LeViT: a Vision Transformer in ConvNet’s Clothing for Faster Inference by Benjamin Graham, Alaaeldin El-Nouby, Hugo Touvron, Pierre Stock, Armand Joulin, Hervé Jégou and Matthijs Douze. If you use this code for a paper please cite: @article{graham2021levit, title={LeViT: a Vision Transformer in ConvNet’s Clothing for Faster Inference}, author={Benjamin Graham and Alaaeldin El-Nouby and […]

sparkvis This is a library for visualizing tensors in a plain Python REPL using sparklines. I was sick of having to install jupyter on servers just to see a damn tensor. E.g. the FFT of MNIST looks like this: Quickstart pip3 install -U sparkvis python3 from sparkvis import sparkvis as vis vis(foo) foo can be a torch tensor, tf tensor, numpy array, etc. It supports anything with a .numpy() method. vis(a, b) will put ‘a’ and ‘b’ side by side. […]

lacmus The program for searching through photos from the air of lost people in the forest using Retina Net neural nwtwork. The project is being developed by a non-profit organization Liza Alert. Demonstration Picture 1 Picture 2 Training data You can download Lacmus Drone Dataset (LaDD) from mail.ru cloud You also can download Lacmus version of Stenford Drone Dataset (SDD) from mail.ru cloud GitHub https://github.com/lacmus-foundation/lacmus    

pytorch_connectomics The field of connectomics aims to reconstruct the wiring diagram of the brain by mapping the neural connections at the level of individual synapses. Recent advances in electronic microscopy (EM) have enabled the collection of a large number of image stacks at nanometer resolution, but the annotation requires expertise and is super time-consuming. Here we provide a deep learning framework powered by PyTorch for automatic and semi-automatic semantic and instance segmentation in connectomics, which is called PyTorch Connectomics (PyTC). […]

CVZone This is a Computer vision package that makes its easy to run Image processing and AI functions. At the core it uses OpenCV and Mediapipe libraries. Installation You can simply use pip to install the latest version of cvzone. pip install cvzone 60 FPS Face Detection import cvzone import cv2 cap = cv2.VideoCapture(0) detector = cvzone.FaceDetector() while True: success, img = cap.read() img, bboxs = detector.findFaces(img) print(bboxs) cv2.imshow(“Image”, img) cv2.waitKey(1) Hand Tracking Basic Code Example import cvzone import cv2 […]

visualize-actions-matrix-builds-on-k8s This repository contains various GitHub Action workflows to trigger Matrix builds on self-hosted GitHub Action runners and visualize their outputs and pod allocations on LED matrices connected to Raspberry PI. Similar visualization scripts are also available for desktop PCs. Watch a one minute video how runners spin up based on a GitHub matrix build, wtach their pods in Kubernetes and see how they stream their work to a widget. … and another movie showing the LED matrix showing the […]

ID Verification by LibraX.ai This is the first free Identity verification in the market. LibraX.ai is an identity verification platform for developers. This solution is to verify user ID image for name matching, age, and basic fraud detection for ID. LibraX is providing to give this service for free as long as we are in business, and you can reach out to [email protected] for any add-on features or customized requirement. How to use the API? For ID Verfication use the […]