Hugging Face's logo

sasha
/
swin-tiny-finetuned-dogfood

Image Classification
Transformers
PyTorch
TensorBoard
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
4
swin-tiny-finetuned-dogfood / README.md
autoevaluator's picture
autoevaluator HF staff
Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator
181877b
preview code
|
raw
history blame
6.28 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - imagefolder
  - lewtun/dog_food
metrics:
  - accuracy
model-index:
  - name: swin-tiny-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: 0.988
            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: 0.9826666666666667
            name: Accuracy
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiM2NjZGY1YWIwZWM5ZGZkZDY0N2Y0NWU4NDIxYjAwNzBhZTY5NTJjMzk0MzM2NjUwNWVmNzYxM2IyMDAxNGMwOSIsInZlcnNpb24iOjF9.53Cl9fYxpPJXt6eEB5arz_aIX7X3N9YJ2-3mpdT7vuOBItQIr4w8y2cCgh_2tt3AesJ9xdTTWVB_H_PIbeKhAQ
          - type: precision
            value: 0.9820904286553143
            name: Precision Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDQ0YzgxOGM0NjRlNzBlOTg5NzYzMDA4NzY1Yjc1MzVhN2ZlZDRkYjAwMzllZTVhZGQyOGRmNTU2YjA0MjJlZSIsInZlcnNpb24iOjF9.7XsjtgztcjGOW_o-MBtcUa4IYtvEYzLB1mN9nXUwlxY4MOx5w3KEdpCkxrmGxOws-n6xCZuqw48RAPqqcPNsBA
          - type: precision
            value: 0.9826666666666667
            name: Precision Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiY2VmYTY3OWIwMjQzNmZmYWI3ZWUyYmI1NTcxZmQ5NTY0ZTNhMDVlYzY3MTFmOTBmNzZjMGM4ZTc4MzUzNzUxOSIsInZlcnNpb24iOjF9.X2WvuzqDpuo_bGxtapAFZJJJ6EIlwPVWUdARCdqgkJeDEaMzIuwduKi7h4SuBDh0g4F28b3VfRCTp90lT1MsAw
          - type: precision
            value: 0.9828416519866903
            name: Precision Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjllYzA5NGIxZDg0M2E4MTM4ZDQ1MjBjODBjNDliMDIxZWEyOWNiYmJhMGZmZjZlMDZlMThmYjIwZTdjM2YyMCIsInZlcnNpb24iOjF9.FDWSnZmrXS-PKVgH6vETcZpLZAa-DyJIohM7guPwa5UzmRSUS1CRr4VGKvGjZrkCa7tP84NrjXU-SuJER_JlAQ
          - type: recall
            value: 0.9828453314981092
            name: Recall Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNzI0NTViZmM1MTRlOTYzYjhlZTE5MWI4MmFkZWJlN2JiZTFiOTViNWNjOGVjYWQ0ZDgwYmNhN2ZhZDY3YjBkOCIsInZlcnNpb24iOjF9.wvulINmxRqH1oEHspW5gJa_JI6k0Ur50I9CwoTn52loQwQeGWPX_4jEhy16f3gf5yiMdc3nLc6aRr13A6hrNCA
          - type: recall
            value: 0.9826666666666667
            name: Recall Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTI2ZWY3Njk4Y2NlYTYxZjExNjcxMTI1MTA3OGUyZWE3ZDk0MjIxMjM1NGQzMjU1NmEwZGU2MTE3MmFjY2QwMyIsInZlcnNpb24iOjF9.mXjMHLhoGaifeOXhIN7mTcnZVrt-e5OnLxNnR0rWaiUmkMWr5Er-_12-0jYX8E6GC0LtuZmkKnRVhOgq5bNoBA
          - type: recall
            value: 0.9826666666666667
            name: Recall Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTFhM2U3YzQ2OWY2YzM0MjAwZWNhOWU0MzQzN2FkYTJkMDgxY2JiZjhlNTViODk0OTYwNjhkNWI0YjA4ODQwOSIsInZlcnNpb24iOjF9.y6SPvYV2lkZSu5ApaWS_h8G3eZMpkhK1kw5s7eTFF57rDHl_O55tSByBWs8FgLPvMYfnXLjJXv8JscRAetWFBg
          - type: f1
            value: 0.9824101123169301
            name: F1 Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzZmZDNiMTY3ZGQyNWViNjc0YTIzNDY4YmEzM2YwNWVhMjkyYjY4MGYyOThjYjRjZTc2MTc0YWU1YmY3MDc3MCIsInZlcnNpb24iOjF9.MOKwaBASsMCFcY-GYuMahkQD16wWMyF_P2asCvnORCmRc5_1jjbEzpxwxl3cJFHkC3m9R3X93-5w8Z5Wcon_Aw
          - type: f1
            value: 0.9826666666666667
            name: F1 Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWNkNDRiNjEzZmFhM2YyNmZmYjM3YTU3ZTczY2NkMzZhMTlhOTA4ZmFlZThhMjQzMjYyNWNmNzQ3YjNjMGZjYiIsInZlcnNpb24iOjF9.J6VNC-vYn1IwPw1MMOhyePD-IxQXSwId5ONvEAzS9L7EaqtgFfFLbYriIJIFiZ1k2MhOezhq9x97W3eMrusnBQ
          - type: f1
            value: 0.9826983433609648
            name: F1 Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTViMzc4YTY4ZDBjYjViMzZkMzBmY2I5ODc3YWZkNWMwZDEwMDM4MmM3YWQ0NDhlNWJkNmMxYjZkN2ZkMDE3OCIsInZlcnNpb24iOjF9.Jjc8YlFFgST-lO24XAAM4O8chHXm5dtBkXv27dddm59hPQIJmwoQF2V4lm5PA_FCtw0UT_2OF4GOyFZT1Kf6DQ
          - type: loss
            value: 0.2326570302248001
            name: loss
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjM1NjgxNjVlMzY4MGYyMTk4OWE5OWJkM2FlNmYzYjIzNzRiMGQzZDg1ZTQ3ZDI0MzBhMTFmOWYyOWYzMTIwOSIsInZlcnNpb24iOjF9.Q9WNaaAyzJ9OA8thqhTtrQhd1fFE4C650WXB3DqJWokZvW9xvhXfReQNQ-RVmXWNjJ2a6oQf0yERhKUTc3xaDg
          - type: matthews_correlation
            value: 0.974016655798285
            name: matthews_correlation
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDRiYzUwOTc1OGI0ODdmOWJhZjU3YTM3MTFkODljNzJhMzMwMTBkYTExZWMyNDkzODM1YTYyYzU3M2I0NjY5YyIsInZlcnNpb24iOjF9.UmUudBnCQRaAe-eA2ZHG3JQ2DodIgxxD5faXqUeBR_FwF1JEvNOLdH15-IkHj8yG7Wh-hl8LrsGeGnlkG56cBw

swin-tiny-finetuned-dogfood

This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the lewtun/dog_food dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1959
  • Accuracy: 0.988

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
0.8198 1.0 16 0.1901 0.9822

Framework versions

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