Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · nateraw

food

nateraw food is a ViT image-classification fine-tune from nateraw. According to the model card, it adapts google/vit-base-patch16-224-in21k on the Food-101 dataset and reports 0.8913 evaluation accuracy.

Publisher
nateraw
Task
image-classification
Model type
vit
License
apache-2.0
Library
transformers
Publication status
Accepted · not indexed

Model overview

nateraw food is published by nateraw as an image-classification fine-tune. The captured configuration identifies ViTForImageClassification with a vit model type. According to the model card, it is a fine-tuned version of google/vit-base-patch16-224-in21k on the nateraw/food101 dataset.

Recorded capabilities

Food-101 fine-tune lineage

According to the model card, the model fine-tunes google/vit-base-patch16-224-in21k on the nateraw/food101 dataset.

Published evaluation results

According to the model card, the evaluation set reports 0.4501 loss and 0.8913 accuracy, with epoch-by-epoch validation loss and accuracy.

Documented training setup

The card lists learning rate 0.0002, train and eval batch size 128, seed 1337, Adam optimizer, linear scheduler, five epochs, and native AMP.

Use cases in the source record

  • Food-101 image classification for dish-recognition experiments using the documented ViT fine-tune.

Limitations and unknowns

  • No parameter count was extracted from this record.
  • Intended uses, limitations, and training data details are marked as more-information-needed in the captured card text.
  • Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: nateraw/food

Captured: Unknown. Processed: 2026-09-07T19:34:52.845456+00:00.

nateraw/food This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the nateraw/food101 dataset. It achieves the following results on the evaluation set: Loss: 0.4501 Accuracy: 0.8913 Model description More information needed Intended uses & limitations More information needed Training and evaluation data More information needed Training procedure Training hyperparameters The following hyperparameters were used during training: learning_rate: 0.0002 train_batch_size: 128 eval_batch_size: 128 seed: 1337 optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 lr_scheduler_type: linear num_epochs: 5.0 mixed_precisi…

F001F002F003F004F005F006F007F008F009F010F011F012