Cross-platform installer for Triton and SageAttention on ComfyUI. Simplifies GPU-accelerated inference setup for Windows users with automated dependency management and RTX 5090 support.
机器学习 · GitHub
发现模型训练、评估与推理框架,比较深度学习和机器学习项目的社区关注度。
实用 GitHub 项目
Tensorflow Faster R-CNN for Windows/Linux and Python 3 (3.5/3.6/3.7)
UER-py
dbiir
Open Source Pre-training Model Framework in PyTorch & Pre-trained Model Zoo
- Reproducibility UER-py has been tested on many datasets and should match the performances of the original pre-training model implementations such as BERT, GPT-2, ELMo, and T5.
- Model modularity UER-py is divided into the following components: embedding, encoder, target embedding (optional), decoder (optional), and target. Ample modules are implemented in each component. Clear and robust interface allows users to combine modules to construct pre-training models with as few restrictions as possible.
bolt
dblalock
DAC-JAX
DBraun
JAX Implementations of Descript Audio Codec and EnCodec
gcn_tutorial
dbusbridge
A tutorial on Graph Convolutional Neural Networks
dcai-lab
dcai-course
Lab assignments for Introduction to Data-Centric AI, MIT IAP 2024 👩🏽💻
Python tutorials as Jupyter Notebooks for NLP, ML, AI
SlicerAutomatedDentalTools
DCBIA-OrthoLab
CC6204
dccuchile
Material del curso de Deep Learning de la Universidad de Chile
PortfolioOptimisers.jl
dcelisgarza
Portfolio optimisation library for Julia. Over 50 risk measures (CVaR, EVaR, RLVaR, drawdown, OWA), hierarchical risk parity, HERC, nested clustered optimisation, risk budgeting, near-optimal centering, four Black-Litterman variants, entropy pooling, factor and high-order priors, denoising, and JuMP-backed convex and non-convex optimization.
eth-cs-notes
dcetin
Lecture notes and cheatsheets for Master's in Computer Science at ETH Zurich
malware-detection
dchad
Always sparse. Never dense. But never say never. A Sparse Training repository for the Adaptive Sparse Connectivity concept and its algorithmic instantiation, i.e. Sparse Evolutionary Training, to boost Deep Learning scalability on various aspects (e.g. memory and computational time efficiency, representation and generalization power).
DeepPiCar
dctian
numpy-ml
ddbourgin
使用 NumPy 实现的机器学习
emotion2vec
ddlBoJack
ml-peg
ddmms
ML Performance and Extrapolation Guide (reference deployment https://ml-peg.stfc.ac.uk)
TSFpaper
ddz16
2020-CBMS-DoubleU-Net
DebeshJha
Official implementation of DoubleU-Net for Semantic Image Segmentation in TensorFlow & Pytorch (Nominated for Best Paper Award (IEEE CBMS))
ResUNetPlusPlus
DebeshJha
Official code for ResUNetplusplus for medical image segmentation (TensorFlow & Pytorch implementation)
cords
decile-team

Reduce end to end training time from days to hours (or hours to minutes), and energy requirements/costs by an order of magnitude using coresets and data selection.
- 3x to 5x speedups, cost reduction, and energy reductions in the training of deep models in supervised learning
- 3x+ speedups, cost/energy reduction for deep model training in semi-supervised learning
CATCH
decisionintelligence
[ICLR 2025] CATCH: Channel-Aware Multivariate Time Series Anomaly Detection via Frequency Patching
DUET
decisionintelligence





