face_landmark
610265158
A simple method for face alignment based on wingloss and mutitask learning :)
Explora herramientas para entrenar, evaluar y ejecutar modelos, y compara el interés de la comunidad.
610265158
A simple method for face alignment based on wingloss and mutitask learning :)
610265158
649453932
Clasificación de textos en chino con TextCNN, TextRNN, FastText, TextRCNN, BiLSTM_Attention, DPCNN y Transformer, basada en PyTorch y lista para usar.
666DZY666

micronet es una biblioteca de compresión y despliegue de modelos. Incluye: 1) cuantización: entrenamiento consciente de la cuantización (QAT), cuantización High-Bit (>2b) (DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference), cuantización Low-Bit (≤2b) ternaria y binaria (TWN/BNN/XNOR-Net), y cuantización posterior al entrenamiento (PTQ) de 8 bits (tensorrt); 2) poda de canales en convoluciones normales, regulares y por grupos; 3) estructuras de convolución por grupos; y 4) fusión de batch normalization para la cuantización. El despliegue admite TensorRT, fp32/fp16/int8 (ptq-calibration), op-adapt (upsample) y dynamic_shape.
7ka-Hiira
Japanese input method for fcitx5, powered by azooKey engine
86maid
920232796
996refuse
99sbr
Completely Scalable FastAPI based template for Machine Learning, Deep Learning and any other software project which wants to use Fast API as an API framework.
Attention OCR Based On Tensorflow
a-martyn
Solutions to labs and excercises from An Introduction to Statistical Learning, as Jupyter Notebooks.
a-r-j
a-r-j
a-r-j

Benchmarking framework for protein representation learning. Includes a large number of pre-training and downstream task datasets, models and training/task utilities. (ICLR 2024)
A3Data
ML made simple
a7medev
React Native On-Device Machine Learning w/ Google ML Kit
Aa-bN
aai-institute
AAitorG

This repository provides DINOSim, a method that leverages the DINOv2 foundation model for zero-shot object detection and segmentation in bioimage analysis. DINOSim uses pretrained DINOv2 embeddings to compare patch similarities, allowing it to detect and segment unseen objects in complex datasets with minimal annotations.
AakashKumarNain
AakashKumarNain
All about the fundamental blocks of TF and JAX!
AaltoML
Bayes-Newton—A Gaussian process library in JAX, with a unifying view of approximate Bayesian inference as variants of Newton's method.
AaltoVision
A PyTorch implementation of "DGC-Net: Dense Geometric Correspondence Network"
aamini
Learn fast, scalable, and calibrated measures of uncertainty using neural networks!