RegNet-Y-064 Open-Source Vision Model - Trained on ImageNet-1k for Efficient Vision Task Processing

Home

Regnet Y 064

Developed by facebook

RegNet model trained on ImageNet-1k, an efficient vision model designed through neural architecture search

Image Classification

Transformers

Open Source License:Apache-2.0 #Neural Architecture Search #Image Classification Optimization #Efficient Network Design

Downloads 17

Release Time : 3/18/2022

Model Overview

RegNet is an image classification model proposed by Facebook Research, optimized through neural architecture search (NAS) by designing search spaces. The model is trained on the ImageNet-1k dataset and is suitable for general image classification tasks.

Model Features

Neural Architecture Search Design

Automatically discovers efficient network architectures through systematic search space design and constraint optimization

Efficient Image Classification

Trained on ImageNet-1k, capable of accurately recognizing 1000 common object categories

Scalable Architecture

The model design method allows generating variants of different complexities to meet various needs

Model Capabilities

Image Classification

Object Recognition

Use Cases

Computer Vision

General Object Recognition

Recognize common objects in images such as animals, daily items, etc.

Can accurately identify 1000 ImageNet categories

Content Classification

Classify and organize image content

🚀 RegNet

RegNet is a model trained on ImageNet-1K. It offers a solution for image classification tasks, leveraging the research from the paper "Designing Network Design Spaces".

🚀 Quick Start

RegNet model is trained on ImageNet-1K. It was introduced in the paper Designing Network Design Spaces and first released in this repository.

Disclaimer: The team releasing RegNet did not write a model card for this model so this model card has been written by the Hugging Face team.

✨ Features

Tags: vision, image-classification
Datasets: ImageNet-1K

You can try out the model using the following sample images:

📚 Documentation

Model description

The authors design search spaces to perform Neural Architecture Search (NAS). They first start from a high dimensional search space and iteratively reduce the search space by empirically applying constraints based on the best-performing models sampled by the current search space.

model image

Intended uses & limitations

You can use the raw model for image classification. See the model hub to look for fine-tuned versions on a task that interests you.

💻 Usage Examples

Basic Usage

>>> from transformers import AutoFeatureExtractor, RegNetForImageClassification
>>> import torch
>>> from datasets import load_dataset

>>> dataset = load_dataset("huggingface/cats-image")
>>> image = dataset["test"]["image"][0]

>>> feature_extractor = AutoFeatureExtractor.from_pretrained("zuppif/regnet-y-040")
>>> model = RegNetForImageClassification.from_pretrained("zuppif/regnet-y-040")

>>> inputs = feature_extractor(image, return_tensors="pt")

>>> with torch.no_grad():
...     logits = model(**inputs).logits

>>> # model predicts one of the 1000 ImageNet classes
>>> predicted_label = logits.argmax(-1).item()
>>> print(model.config.id2label[predicted_label])
'tabby, tabby cat'

For more code examples, we refer to the documentation.

📄 License

This model is licensed under the Apache 2.0 license.

Property	Details
Model Type	RegNet
Training Data	ImageNet-1K

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご