Projects using PyTorch
Projects using PyTorch
Sign Up
Post a job
Sign Up
Log In
Filters
1
Projects
People
0
Nikola Gojakovic
Text-to-Image Diffusion Model Training
0
12
0
Aaron Segiel
CIFAR-10 Image Classification with CNN
0
8
0
Anastasiya Kotelnikova
Spiking Neural Networks with PyTorch & Norse
0
4
0
Badaruddin Chachar
Wav2Lip Video Generation Pipeline
0
5
0
Kavit Tolia
AI Hangman Game Development
0
2
0
Eyad Gad
Yolov5 + Deep Sort with PyTorch
0
15
0
Franco Mucco
Real time Segmentation
0
9
2
William Alabi
DEWSClim: A Digital Early Warning System for Farmers
1
2
10
0
Imran Ullah
flower classification using deep learning
0
27
0
zain via Replit
working on ML scalability
0
27
0
Serhii Vysochanskyi
pro
Pinpoint | Discovery AI platform
0
26
0
Aaron Kakembo
The Hybrid Meeting Minutes Generator is an enterprise-grade audio processing tool that transforms raw meeting recordings into structured, executive-level minutes. Engineered with a 'Hybrid' operational paradigm, the system allows users to seamlessly toggle between 100% private, ultra-fast local inference using quantized open-source models, or route data to premium cloud APIs (OpenAI/Gemini) for maximum fidelity.
0
34
0
Avneet Singh
Voice Controlled AI Chatbot using Selenium and Rasa
0
37
0
Pooja Shah
Document Processing with OCR and structured data extraction Developed a enterprise grade SaaS app for structured data extraction by advanced OCR from docs. HIPAA complaint solution developed. Developed backend using Python FastAPI and frontend with react typescript, OCR using advanced ML/DL techniques and LayoutLM, LLM OCR and more.... Advanced Computer vision techniques applied.
0
6
0
Karan Singh
Scientific Image Forgery Detection — Kaggle Competition Participated in the ongoing Kaggle competition on Copy-Move Forgery Detection in Scientific Images, aimed at identifying manipulated biomedical figures that can compromise research integrity. For this challenge, I developed a ResNet50 + U-Net hybrid segmentation model using PyTorch, designed to detect and segment forged regions at the pixel level. My approach combines Dice and Focal losses for balanced training, WeightedRandomSampling to oversample forged images, and Test-Time Augmentation (TTA) to improve prediction robustness. Achieved an initial score of 0.303 on the public leaderboard. I’m continuing to experiment with architecture tuning, learning rate schedules, and other loss functions to further enhance performance and generalization.
0
58
1
Ebenge Usip
Harnessing AI to Unlock the Creative Potential of Music
1
1
Explore projects
