pranavgupta2603

pranavgupta2603.github.io

prd-chatpgpt-api

profile_photo

project-classification-ai-ml

q-crusaders

research-pathway-predictor

searchbrowserhistorygpt

seoanalyzergpt

ship-classification

simclr-urbansound8k

Explore advanced audio classification with SimCLR-UrbanSound8K. This repository applies SimCLR for urban sound categorization using the UrbanSound8K dataset, demonstrating state-of-the-art techniques in deep learning and audio analysis

slic

SLIC Paper Python Implementation: https://ieeexplore.ieee.org/abstract/document/6205760

smartbharitya-sih23

splitwisegptvision

SplitwiseGPT Vision: Streamline bill splitting with AI-driven image processing and OCR. This innovative web app uses Pytesseract, GPT-4 Vision, and the Splitwise API to simplify group expense management. Upload bill images, auto-extract details, and seamlessly integrate expenses into Splitwise groups. Ideal for easy and accurate financial tracking

stable-dffusion-finetuning-flowers

A tutorial that guides users through the process of fine-tuning a stable diffusion model using HuggingFace's diffusers library. The tutorial includes advice on suitable hardware requirements, data preparation using the BLIP Flowers Dataset and a Python notebook, and detailed instructions for fine-tuning the model.

stable-diffusion

surveillanceapp_noctoders-

urbansound8k-melspectrogram

The GitHub repository focuses on transforming audio files into mel-spectrogram images. It was created for the "UrbanSound8k Mel Spectrogram Images" dataset on Kaggle. Key features include sound visualization and dataset creation for sound analysis. The repository includes an Audio-to-Spectrogram.ipynb notebook for creating spectrograms.

verbose-guacamole

vqa-implementation

writetrack