food

nateraw/food

food is a image classification model from nateraw. Use it when you need a label for an image. It is set up for transformers. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

4.7K

0% of all-time downloads

All-time downloads

Public

Repo size

687 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin344 MB · 100%

At a glance

Task: Image Classification
Library: transformers
License: apache-2.0
Model type: vit
Access: Public
Created: Mar 2, 2022
Updated: May 17, 2022
SHA: 8991abd4

Datasets

food101

Spaces

100 linked

Model card

From the Hugging Face model README

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_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.8271	1.0	592	0.6070	0.8562
0.4376	2.0	1184	0.4947	0.8691
0.2089	3.0	1776	0.4876	0.8747
0.0882	4.0	2368	0.4639	0.8857
0.0452	5.0	2960	0.4501	0.8913

Framework versions

Transformers 4.9.0.dev0
Pytorch 1.9.0+cu102
Datasets 1.9.1.dev0
Tokenizers 0.10.3

Task: Image Classification
Library: transformers
Type: vit
License: apache-2.0
Hf Inference: live
Created: Mar 2, 2022
Updated: May 17, 2022