README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - imagefolder
  - lewtun/dog_food
metrics:
  - accuracy
base_model: microsoft/resnet-18
model-index:
  - name: resnet-18-finetuned-dogfood
    results:
      - task:
          type: image-classification
          name: Image Classification
        dataset:
          name: lewtun/dog_food
          type: lewtun/dog_food
          args: lewtun--dog_food
        metrics:
          - type: accuracy
            value: 0.896
            name: Accuracy
      - task:
          type: image-classification
          name: Image Classification
        dataset:
          name: lewtun/dog_food
          type: lewtun/dog_food
          config: lewtun--dog_food
          split: test
        metrics:
          - type: accuracy
            value: 0.8466666666666667
            name: Accuracy
            verified: true
          - type: precision
            value: 0.8850127293141284
            name: Precision Macro
            verified: true
          - type: precision
            value: 0.8466666666666667
            name: Precision Micro
            verified: true
          - type: precision
            value: 0.8939157698241645
            name: Precision Weighted
            verified: true
          - type: recall
            value: 0.8555113273379528
            name: Recall Macro
            verified: true
          - type: recall
            value: 0.8466666666666667
            name: Recall Micro
            verified: true
          - type: recall
            value: 0.8466666666666667
            name: Recall Weighted
            verified: true
          - type: f1
            value: 0.8431399312051647
            name: F1 Macro
            verified: true
          - type: f1
            value: 0.8466666666666667
            name: F1 Micro
            verified: true
          - type: f1
            value: 0.8430272582865614
            name: F1 Weighted
            verified: true
          - type: loss
            value: 0.3633290231227875
            name: loss
            verified: true
          - type: matthews_correlation
            value: 0.7973101366252381
            name: matthews_correlation
            verified: true

resnet-18-finetuned-dogfood

This model is a fine-tuned version of microsoft/resnet-18 on the lewtun/dog_food dataset. It achieves the following results on the evaluation set:

• Loss: 0.2991
• Accuracy: 0.896

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: 5e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.846	1.0	16	0.2662	0.9156

Framework versions

• Transformers 4.20.1
• Pytorch 1.11.0+cu113
• Datasets 2.3.2
• Tokenizers 0.12.1