Mixelll

fasthtml

The fastest way to create an HTML app

RAG_Techniques

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and contextually rich responses.

gritlm

Generative Representational Instruction Tuning

lag-llama

Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting

ai-for-employees

Employees who do not use AI will be replaced by employees who do use AI.

BLIP

PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

LAVIS

LAVIS - A One-stop Library for Language-Vision Intelligence

Merlin

NVIDIA Merlin is an open source library providing end-to-end GPU-accelerated recommender systems, from feature engineering and preprocessing to training deep learning models and running inference in production.

courses

fast.ai Courses

FizzBuzzEnterpriseEdition

FizzBuzz Enterprise Edition is a no-nonsense implementation of FizzBuzz made by serious businessmen for serious business purposes.

pix2seq

Pix2Seq codebase: multi-tasks with generative modeling (autoregressive and diffusion)

simclr

SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners

asen

cloth-identifier

DeepFashion

Implementation of a convolutional neural network model on real life data (self-taken images). Using transfer learning technique with a pre-trained model (VGG16) to classify images of clothing, built by Keras, Python.

CNN-Image-classification-Using-Fashion-MNIST-dataset

There's been much speculation in recent years about neural networks technologies and other deep learning algorithms, primarily because of the popularity of several implementations in the sector utilizing these techniques. Consequently, this hype has yielded several innovative ideas to build open-source libraries and methods to enable the average income tech-savvies to achieve their objective. This research paper aims to examine and illustrate how to use deep learning technologies and algorithms to precisely classify a dataset of fashion images into their respective clothing categories. First, the paper shows the general knowledge of convolutional neural networks (CNN) and the techniques of image classification. Later on, it also discusses the methodology of building a neural network and the simulation process. The results of the neural network simulation are compressively evaluated and discussed.

dress-pattern-recognition-using-CNN

An image recognition model which is capable of identifying the pattern on a dress image

clothing-detection-ecommerce-dataset

Clothing detection dataset

Air-Clothing-MA

Detection and recognition of multiple human attributes

asenpp

fashion-landmarks

Fashion Landmark Detection in the Wild

fashion-cut

Fashion Cut in the Wild (Clothes Cutout System)

DeepFashion-MultiModal

A large-scale high-quality human dataset with rich multi-modal annotations

deepfashion_ninecat

Extended Annotations of DeepFashion Images for Fine-grained Recognition

deepfashion_dataset

TensorFlow build script for the deep fashion dataset, depends on glove embeddings.

mmfashion

Open-source toolbox for visual fashion analysis based on PyTorch

DeepFashion

Apparel detection using deep learning

tripletNet

Image retrieval with triplet loss

pytorch-deepfashion

pytorch implementation of the deepfashion architecture (https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Liu_DeepFashion_Powering_Robust_CVPR_2016_paper.pdf)

fashion-recommendation

A clothing retrieval and visual recommendation model for fashion images.