Convnext Small.in12k Ft In1k is an image classification model hosted on Hugging Face as part of the timm PyTorch Image Models collection. It was pretrained on the ImageNet-12k dataset and fine-tuned on ImageNet-1k, as indicated by its name and associated tags. The model carries an arxiv reference to paper 2201.03545.
It can be loaded and run through the timm library by calling timm.create_model with the identifier "hf_hub:timm/convnext_small.in12k_ft_in1k" and pretrained set to True. The same model is also accessible via the Hugging Face Transformers library, either through a high-level image-classification pipeline that accepts image URLs or by directly instantiating it with AutoModel.from_pretrained, including support for automatic device mapping. Example code demonstrates inference on a sample parrot image from the Hugging Face documentation dataset.
The model is provided in PyTorch and Safetensors formats. It is published under the Apache-2.0 license. No pricing information is stated because the model is available for direct download and local or hosted use through the open Hugging Face platform.
Convnext Small.in12k Ft In1k sits in PulseGate's Other AI category. It focuses on performing high-accuracy image classification using a modern ConvNeXt convolutional network. It is built as an open-source project for developers. The project is open source (Apache-2.0). It runs on the web and API.
It is developed by timm, and it first shipped in 2019. The project is developed in the open on GitHub with 37k stars and 49 commits in the last 90 days. Among its 3 catalogued features are Image Classification, ConvNeXt Architecture, and Pretrained Weights.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do