metadata

license: apache-2.0
tags:
  - image-classification
  - generated_from_trainer
datasets:
  - imagefolder
  - rajistics/indian_food_images
metrics:
  - accuracy
widget:
  - src: >-
      https://huggingface.co/rajistics/finetuned-indian-food/resolve/main/003.jpg
    example_title: Example1
model-index:
  - name: finetuned-indian-food
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: indian_food_images
          type: imagefolder
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9521785334750266

finetuned-indian-food

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the indian_food_images dataset. It achieves the following results on the evaluation set:

Loss: 0.2139
Accuracy: 0.9522

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: 16
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 4
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.0846	0.3	100	0.9561	0.8555
0.7894	0.6	200	0.5871	0.8927
0.6233	0.9	300	0.4447	0.9107
0.3619	1.2	400	0.4355	0.8937
0.34	1.5	500	0.3712	0.9118
0.3413	1.8	600	0.4088	0.8916
0.3619	2.1	700	0.3741	0.9044
0.2135	2.4	800	0.3286	0.9160
0.2166	2.7	900	0.2758	0.9416
0.1557	3.0	1000	0.2679	0.9330
0.1115	3.3	1100	0.2529	0.9362
0.1571	3.6	1200	0.2360	0.9469
0.1079	3.9	1300	0.2139	0.9522

Framework versions

Transformers 4.20.1
Pytorch 1.12.0+cu113
Datasets 2.3.2
Tokenizers 0.12.1