Mobilevit Xxs Food101 is a PyTorch model designed for image classification tasks, specifically trained on the Food-101 dataset. The model uses the MobileViT-XXS architecture and is provided as a raw training checkpoint file, which can be found as MobileViT-XXS-food101.pt. The associated configuration files are also included from the training run. The dataset used for training is the Food-101 dataset, which is commonly used for food image recognition tasks. Performance metrics from training indicate that the model achieved an Acc@1 of 65.42% and Acc@5 of 87.77% on the training set, and 62.42% and 86.32% respectively on the validation set. The model is released under the MIT license. This checkpoint is not deployed by any inference provider and is intended for those who wish to use or further develop the model for image classification applications involving food images. No additional deployment, integration, or usage details are provided beyond the availability of the raw checkpoint and configuration files.
In the Other AI space, Mobilevit Xxs Food101 takes a focused approach. It focuses on automating food image classification using a lightweight MobileViT model. It is built as an open-source project for machine learning researchers. Mobilevit Xxs Food101 is open source under the Open Source license. The product ships for the web.
It is developed by mnjm, and the product first shipped in 2025. Development happens publicly on GitHub with 6 commits in the last 90 days. PulseGate's similarity index finds few close equivalents — Mobilevit Xxs Food101 occupies a relatively distinct niche. Key capabilities include image classification, mobileViT architecture, and food-101 dataset.
Latest indexed changes and source events
mnjm/mobilevit-xxs-food101 discovered by the PulseGate indexer
Other apps tracked under the same category.