Hugging Face's logo

douwekiela
/
resnet-18-finetuned-dogfood

Image Classification
Transformers
PyTorch
TensorBoard
resnet
Generated from Trainer
Eval Results
Model card Files Metrics Community
4
resnet-18-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
cce9a0b
preview code
|
raw
history blame
6.25 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - imagefolder
  - lewtun/dog_food
metrics:
  - accuracy
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
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTIwY2IwOWM2YjgzNjU4YmU5NjBhN2QxMzQ2NzhlM2MzNWY1ZTFhMjYyNWM5ZGM2MjcxY2ViNjRkMGJmZTRhNSIsInZlcnNpb24iOjF9.Ydnujkcb-gT5T6r8-9FhRZgKh4l3tVIO87ZP8kzQrF74UfeJya-Ai36a_TGf1HMQNVklNP7FD3fr7eX-KZ3FCg
          - type: precision
            value: 0.8850127293141284
            name: Precision Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiN2I5ZWYxYjc5MWQ0YTRlODdiNjg1NTJlMjVkODExOGRkNmJkYzQ2MmY0NmIxNGExZjY3OTcyNGUwMGYxZWJmMSIsInZlcnNpb24iOjF9.vUlq5ppw_Cp-j5gYxIhuixJqRsflwUXZJmVBxTpQ2EXuLjjslOjlAQ6uqX9Gk-RjCmZgrX_anXWre2JQnYEWBQ
          - type: precision
            value: 0.8466666666666667
            name: Precision Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTNmNjVmYzczZmVjODg0NGJmNDg4YWRiMTJhYmI5ZDFlMzYxN2I2MThkZTEyZTdkZDRmN2QwMGNmNjljZDMwMCIsInZlcnNpb24iOjF9.eY_2irXgvpJlIgqXm1eIbR_1048f160NTjXNeaSP94WmEDpxoaR-2S5MgjV7jwWJkfg0ITE8CBudQ9eFJgRwAA
          - type: precision
            value: 0.8939157698241645
            name: Precision Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiN2U4MmJmZWUyYzk2NTQ1NjlkZjYyZGIyYjdlOWI4MDM0MzAzMjhiNWE3ZWU4NGRkMDUzMjI3MDM1Mzg0YWMzNCIsInZlcnNpb24iOjF9.CHWxbXYbIewtrWln29_w6Rggqw7av4GF8OPutIATK8wo4bz6EX3Qw4g5cvzSl1jNjf9K1QVvq_p9o4-TDrHeCA
          - type: recall
            value: 0.8555113273379528
            name: Recall Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTIzODI3ZTc1NzlkNTY5MTc1MzFjMzBjMWI4MzkyYmUzZWY0MGEwYTNiOTU5NzQwMjNiNzYyYzU5MmY1N2I2ZCIsInZlcnNpb24iOjF9.5OrJ16GgPdOh_jWlCKAHBs6Xf-X-AV-Q3Xw3c0yvbX15IVLW2ZOEfNILPkYJRRIIGme6X0GPIs7xXqf3p3leCg
          - type: recall
            value: 0.8466666666666667
            name: Recall Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDliNTBmOTg3MDMzYTAzMTMwZjM2MWMwNmYwNjg4NGQxMGIyODNhMDYxYmI4YWVkODBmMTZhOWI2ZDc1YzA5NCIsInZlcnNpb24iOjF9.19ZNnknqA5y7xJ4d8vo-6pWoxY-bgV7Fi2PMWfHpz7IeIE1Q-UXocc_d3QdBD_CT_LR7iDmRTnh2laeR7_PfAA
          - type: recall
            value: 0.8466666666666667
            name: Recall Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOGZjODVkZTJkYTVkY2JlNTc1NTc1NWNjNDZiNzk5ZjMwNjJmMmY3OWVlNDFiNzQ3NzRlODExMGE1ZTY3MjZmNiIsInZlcnNpb24iOjF9.-aSeNHDPVM8PyOtZJLGGXjF8wdSfiHqJVv7dgGRTWO9colKaA0IdsXVF8ObXQxDugpp086S3SzGJNUCejJ6pCg
          - type: f1
            value: 0.8431399312051647
            name: F1 Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYTE3YTJjNDJhMGU0YTU3ZjE5MGZiNzdkN2UwZmY5YzA4MjRmNDg3YTg5N2Y5ZDI5OTNiMDRmODk3NjJmNDkxMSIsInZlcnNpb24iOjF9.I6syUyV2vCYamp2Y-R2Ed-YsT1j9SGpq9bnkCOgrbVNIGA7olqqXUltpqea_g1Kf1j8xGQkAlkKBIGaZ1LDiBw
          - type: f1
            value: 0.8466666666666667
            name: F1 Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTRmYTU4NDcwNzMzOGQxOGJkNGViZjhlYWQwMjZjOTRiODM2YTI1MGQzZGEzY2Y5NzFiNTFlYWMyZTBhNjI2OCIsInZlcnNpb24iOjF9.92EakZFNqp_DyYghX1uRbWxTK7iszc31XKcqMz4ah5Nn4q9yE1e5PwmpN9CfTQ1WBMrjQZfC6WMjZlKMCbDDBQ
          - type: f1
            value: 0.8430272582865614
            name: F1 Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNGIzYTUwZTI2ZjA0NTAwZDExNTI0ZTc1NWIwODE4NGZhNGUwYjUzMWZkMDU2NTZkNzc1NjkwN2NiYzg0MGVkMyIsInZlcnNpb24iOjF9.eRKxOW4LRNL-xsmzrujmZp8V_TPPO8PlzW6SK72cymBhmf-VCOwCfn1_sDRwvswvVPr1r5hG2ViPH5JlPiiiCQ
          - type: loss
            value: 0.3633290231227875
            name: loss
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDM3NjQwYTM0YTc0NjRiOWI3ZjZjN2IxNzZjMWYzMDc4NWY1Yjc1N2NjZDUzZWNiMjhhNjhhY2YwMjkxMDkwMSIsInZlcnNpb24iOjF9.DPRH5UxA5P-2wunBjid2deWgwNUm5uub-OuJGznbfUYH4ZMZ_vX17TDPgQ_qx7MG9DidLyhoApG3KTZbC7L4Cw
          - type: matthews_correlation
            value: 0.7973101366252381
            name: matthews_correlation
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTk2M2ZmMTNhYmM3ZTJjOTU2NTIxNTMzNmUxYzE0YmIwZTAyOTMxNjU4YTgwODA2Mzk2YmM4MGZjYTUyMDY3YyIsInZlcnNpb24iOjF9.mTh2Mnkhh1btzRCKN2hESCOSEnof8nvB2V1eTzLhkVM68R2uSmya9c1QFyRty6Yc5SS0oa6yDXVfhJylJ5T-CA

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