dnth

behavior-dataset

Dataset for behavior recognition on NAO

deployment-frameworks

fastdup-manage-clean-curate-blogpost

Find duplicate and anomalies in your dataset. Identify wrong/confusing labels in your dataset. Uncover data leak in your dataset.

huggingface-timm-mobile-blogpost

Bringing High-Quality Image Models to Mobile: Hugging Face TIMM Meets Android & iOS

supercharge-your-pytorch-image-models-blogpost

Supercharge Your PyTorch Image Models: Bag of Tricks to 8x Faster Inference with ONNX Runtime & Optimizations

timm-flutter-pytorch-lite-blogpost

PyTorch at the Edge: Deploying Over 964 TIMM Models on Android with TorchScript and Flutter.

x.infer

Framework agnostic computer vision inference. Run 1000+ models by changing only one line of code. Supports models from transformers, timm, ultralytics, vllm, ollama and your custom model.

x.retrieval

Evaluate your multimodal retrieval system with any models and datasets.

yolov5-deepsparse-blogpost

By the end of this post, you will learn how to: Train a SOTA YOLOv5 model on your own data. Sparsify the model using SparseML quantization aware training, sparse transfer learning, and one-shot quantization. Export the sparsified model and run it using the DeepSparse engine at insane speeds. P/S: The end result - YOLOv5 on CPU at 180+ FPS using on

yolov5-torchscript-flutter-blogpost

YOLOv5 real time inference on Android with Torchscript and Flutter

dnth/x.infer

Framework agnostic computer vision inference. Run 1000+ models by changing only one line of code. Supports models from transformers, timm, ultralytics, vllm, ollama and your custom model.

dnth/supercharge-your-pytorch-image-models-blogpost

Supercharge Your PyTorch Image Models: Bag of Tricks to 8x Faster Inference with ONNX Runtime & Optimizations

dnth/deployment-frameworks

dnth/postgresql-multimodal-retrieval

Vector/Hybrid Search & Retrieval on PostgreSQL database using Vision Language Model.

dnth/cvat-gradio

Load CVAT datasets into Gradio

dnth/design-patterns-in-python

My practice to implement design patterns in Python

dnth/dnth

dnth/dnth.github.io

dnth/ram-onnx-inference

dnth/x.retrieval

Evaluate your multimodal retrieval system with any models and datasets.

dnth/bentoml-model-chaining

Chain multiple models together using BentoML. Run inference with an API endpoint. Deploy anywhere Docker runs.

dnth/self-supervised-timm

Adapt TIMM backbone to your custom dataset with self-supervised learning in fastai

dnth/cv-docker-images

A collection of Dockerfiles to build computer vision containers for deployment.

dnth/data-flywheel

Data flywheel to iteratively correct object detection annotations

dnth/freqtrade

Free, open source crypto trading bot

dnth/from-pytorch-to-edge-deployment-blogpost

In this blog, I show you simple steps to improve your PyTorch model's inference time making them fit to be deployed on the edge.

dnth/icevision

An Agnostic Computer Vision Framework - Pluggable to any Training Library: Fastai, Pytorch-Lightning with more to come

dnth/lightly

A python library for self-supervised learning on images.

dnth/mmdetection_configs

Copy of original mmdetection configs

dnth/moondream

tiny vision language model

dnth/optimum

🚀 Accelerate training and inference of 🤗 Transformers and 🤗 Diffusers with easy to use hardware optimization tools

dnth/portio-hugo

Portio Hugo is a simple, minimal and responsive Portfolio Hugo Theme. Portio Hugo is well organized, well-formatted, and named accordingly so it’s easy to change any and all of the design. Portio is built with Bootstrap 4. You can customize it very easily to fit your needs.

dnth/pylabel

Python library for computer vision labeling tasks. The core functionality is to translate bounding box annotations between different formats-for example, from coco to yolo.

dnth/recognize-anything

Code for the Recognize Anything Model (RAM) and Tag2Text Model

dnth/rpi_inference

Computer vision inference on Raspberry Pi.

dnth/sprout_downloader_python

SproutVideos downloader on python

dnth/streamlit-img-label

streamlit-img-label is a graphical image annotation tool using streamlit. Annotations are saved as XML files in PASCAL VOC format.

dnth/vl-hf-annotation-converter

dnth/vlhf

Visual Layer <-> Hugging Face integration for data in/out.

dnth/yolox-body-head-hand-face