Pytorch-UNet
PyTorch implementation of the U-Net for image semantic segmentation with high quality images
- 12k
- Python
- GPL-3.0
- 2 y ago
PyTorch implementation of the U-Net for image semantic segmentation with high quality images
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
Github repo with tutorials to fine tune transformers for diff NLP tasks
Train a state-of-the-art yolov3 object detector from scratch!
Transformers 3rd Edition
Unofficial PyTorch Implementation for HifiFace (https://arxiv.org/abs/2106.09965)
(ICML 2020) This repo contains code for our paper "Revisiting Training Strategies and Generalization Performance in Deep Metric Learning" (https://arxiv.org/abs/2002.08473) to facilitate consistent research in the field of Deep Metric Learning.
wandbot is a technical support bot for Weights & Biases' AI developer tools that can run in Discord, Slack, ChatGPT and Zendesk
PyTorch Implementations For A Series Of Deep Learning-Based Recommendation Models
Practical Computer Vision Bootcamp with notebooks, quizzes, and videos
Easiest way of fine-tuning HuggingFace video classification models
Deep Learning project template for PyTorch (multi-gpu training is supported)
A convenient way to trigger synchronizations to wandb / Weights & Biases if your compute nodes don't have internet!
Automated question generation and question answering from Turkish texts using text-to-text transformers
(ECCV 2020) This repo contains code for "DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning" (https://arxiv.org/abs/2004.13458), which extends vanilla DML with auxiliary and self-supervised features.
🤖 Project template for your next awesome AI project. 🦾
:detective::robot: Monitoring a PyTorch Lightning CNN with Weights & Biases
PiD-Image-Upscaler is an experimental, advanced super-resolution and image-to-image refinement application based on the state-of-the-art PiD (Pixel Diffusion Decoder) framework by NVIDIA. This application couples local generative text-to-image and image-to-image pipelines.
We use phonetics as a feature to create a joint semantic-phonetic embedding and improve the neural machine translation between Chinese and Japanese. 🥳
Testing ray tune with slurm batch submission and optuna and wandb
Fine-tune LiquidAI LFM2.5 Embedding models for dense retrieval using your own data
A Streamlit-based AI assistant generates custom Streamlit app code from user-provided images or text using the Google Gemini model.
Simple Repository regarding tweet classification using huggingface tokenizer and transformer, and tracking using weights and biases.
A hallucination detection pipeline for Large Language Models (LLMs).
Feature-rich codebase for pretrained language models research in PyTorch and 🤗
VisionTrack AI is a production-grade multi-object detection & tracking app powered by YOLOv8 + BoT-SORT/ByteTrack, featuring a rich interactive Streamlit dashboard with live Plotly analytics, class filtering, MP4 export, and optional W&B logging.