Convnext Small.fb In22k Ft In1k 384 is an image classification model hosted on Hugging Face as part of the timm PyTorch Image Models collection. It carries the identifier timm/convnext_small.fb_in22k_ft_in1k_384 and was trained on the imagenet-22k and imagenet-1k datasets. The model follows the architecture described in the paper with arxiv identifier 2201.03545.
It is delivered as a PyTorch model with Safetensors weights and supports integration through the timm library or the Hugging Face Transformers library. Code examples show creation via timm.create_model with the pretrained flag set to true, as well as loading through the Transformers pipeline for image-classification tasks or directly with AutoModel.from_pretrained. The repository provides instructions for use with libraries, inference providers, notebooks, and local applications.
The model is licensed under apache-2.0. It is maintained under the PyTorch Image Models organization on Hugging Face, which has accumulated 890 likes for the associated collection. No pricing information is stated because the model is openly available for download and local or hosted inference.
In the Other AI space, Convnext Small.fb In22k Ft In1k 384 takes a focused approach. It focuses on providing ready-to-use high-accuracy image classification models for computer vision tasks. It is built as an open-source project for developers. Convnext Small.fb In22k Ft In1k 384 is open source under the MIT license. It ships for the web and API.
timm builds and maintains Convnext Small.fb In22k Ft In1k 384, and it first shipped in 2022. The GitHub repository has been archived. 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