Regnet X 002

🚀 RegNet

A RegNet model trained on ImageNet-1K, introduced in the paper Designing Network Design Spaces and first released in this repository. It can be used for image classification tasks.

🚀 Quick Start

The RegNet model is trained on ImageNet-1K and can be used for image classification. You can find fine - tuned versions on the model hub.

✨ Features

• The authors design search spaces for Neural Architecture Search (NAS). They start from a high - dimensional search space and iteratively reduce it by applying empirical constraints based on the best - performing models sampled from the current search space.
• It provides a new approach for designing neural network architectures.

📦 Installation

No specific installation steps are provided in the original document, so this section is skipped.

💻 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'

Advanced Usage

For more code examples, we refer to the documentation.

📚 Documentation

The model was introduced in the paper Designing Network Design Spaces. The design process involves designing search spaces for Neural Architecture Search (NAS). The authors start from a high - dimensional search space and iteratively reduce it based on the best - performing models sampled from the current search space.

🔧 Technical Details

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.

📄 License

This model is licensed under the Apache - 2.0 license.

⚠️ Important Note

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.