Resnet-50-cifar10-quality-drift Open-source Image Classification Model - Accurately Identify Images of Different Qualities

Resnet 50 Cifar10 Quality Drift

Developed by arize-ai

An image classification model based on the ResNet-50 architecture, fine-tuned on the CIFAR-10 quality shift dataset

Downloads 29

Release Time : 7/21/2022

Model Overview

This model is a fine-tuned version of microsoft/resnet-50 on the CIFAR-10 quality shift dataset, primarily used for image classification tasks.

High-Quality Image Classification

Achieved 72.4% accuracy on the CIFAR-10 quality shift dataset

Fine-Tuning Optimization

Fine-tuned based on the pre-trained ResNet-50 model to adapt to specific datasets

Image Classification

Quality Shift Recognition

Computer Vision

Image Quality Classification

Classify and recognize image quality

Achieved 72.4% accuracy on the evaluation set

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
1.7311	1.0	750	1.1310	0.6333	0.6300
1.1728	2.0	1500	0.8495	0.7153	0.7155
1.0322	3.0	2250	0.8235	0.724	0.7222

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base