compares different pretrained object classification with per-layer and per-channel quantization using pytorch
-
Updated
Jun 12, 2020 - Python
compares different pretrained object classification with per-layer and per-channel quantization using pytorch
ai-zipper offers numerous AI model compression methods, also it is easy to embed into your own source code
Minimal Reproducibility Study of (https://arxiv.org/abs/1911.05248). Experiments with Compression of Deep Neural Networks
Code of the ICASSP 2022 paper "Gradient Variance Loss for Structure Enhanced Super-Resolution"
DA2Lite is an automated model compression toolkit for PyTorch.
This is an End to End project and Api deployment for Spain electricity shortfall prediction
Quantization for Object Detection in Tensorflow 2.x
People Counter App at the Edge
Vision-lanugage model example code.
A comparative analysis of Fast Wavelet Transform (FWT) compression versus traditional compression methods on network performance, focusing on throughput and latency. This project aims to explore the effectiveness of FWT in modern digital communication environments.
Don't Think It Twice: Exploit Shift Invariance for Efficient Online Streaming Inference of CNNs
Llama3.1-8B usage for extraction of symptoms in Danish and English clinical text data and Masking words prediction.
Implementação do algoritmo de retropropagação para treinamento de redes neurais. Este projeto aborda a otimização de modelos de aprendizado profundo para melhorar a precisão das previsões.
PyTorch implementation of normalization-free LLMs investigating entropic behavior to find desirable activation functions
This project focuses on real-time object detection and tracking using the Faster R-CNN model, emphasizing accuracy over speed. It utilizes the COCO 2017 dataset for training, which contains diverse and complex images. The Faster R-CNN model is integrated with FiftyOne for visualizing predictions and ground truth annotations. A custom CentroidTracke
The objective of this project is the development and evaluation of recommendation algorithms based on the MovieLens dataset, one of the benchmark datasets for research into recommendation systems. User ratings, tags, and movie metadata are used in the dataset, allowing for simple and advanced recommendation techniques
This project builds and optimizes a model on a dataset using Ridge regression and polynomial features. Model accuracy is enhanced through regularization and polynomial transformations. Grid search and cross-validation are used to find the best parameters, and the model's performance is evaluated.
Heart disease classification using machine learning algorithms with hyperparameter tuning for optimized model performance. Algorithms include XGBoost, Random Forest, Logistic Regression, and moreto find the best model for accurate heart disease prediction.
Add a description, image, and links to the model-optimization topic page so that developers can more easily learn about it.
To associate your repository with the model-optimization topic, visit your repo's landing page and select "manage topics."