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: Fried Rice
  - src: >-
      https://huggingface.co/rajistics/finetuned-indian-food/resolve/main/126.jpg
    example_title: Paani Puri
  - src: >-
      https://huggingface.co/rajistics/finetuned-indian-food/resolve/main/401.jpg
    example_title: Chapathi
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
      - task:
          type: image-classification
          name: Image Classification
        dataset:
          name: rajistics/indian_food_images
          type: rajistics/indian_food_images
          config: rajistics--indian_food_images
          split: test
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8257173219978746
            verified: true
          - name: Precision Macro
            type: precision
            value: 0.8391547623590003
            verified: true
          - name: Precision Micro
            type: precision
            value: 0.8257173219978746
            verified: true
          - name: Precision Weighted
            type: precision
            value: 0.8437849242516663
            verified: true
          - name: Recall Macro
            type: recall
            value: 0.8199909093335551
            verified: true
          - name: Recall Micro
            type: recall
            value: 0.8257173219978746
            verified: true
          - name: Recall Weighted
            type: recall
            value: 0.8257173219978746
            verified: true
          - name: F1 Macro
            type: f1
            value: 0.8207881196755944
            verified: true
          - name: F1 Micro
            type: f1
            value: 0.8257173219978746
            verified: true
          - name: F1 Weighted
            type: f1
            value: 0.8256340007731109
            verified: true
          - name: loss
            type: loss
            value: 0.6241679787635803
            verified: true

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