Hugging Face's logo

nateraw
/
vit-base-beans

Image Classification
Transformers
PyTorch
TensorBoard
English
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
7
vit-base-beans / README.md
librarian-bot's picture
librarian-bot
Librarian Bot: Add base_model information to model
c145e62
preview code
|
raw
history blame
6.34 kB
metadata
language: en
license: apache-2.0
tags:
  - generated_from_trainer
  - image-classification
datasets:
  - beans
metrics:
  - accuracy
widget:
  - src: https://huggingface.co/nateraw/vit-base-beans/resolve/main/healthy.jpeg
    example_title: Healthy
  - src: >-
      https://huggingface.co/nateraw/vit-base-beans/resolve/main/angular_leaf_spot.jpeg
    example_title: Angular Leaf Spot
  - src: https://huggingface.co/nateraw/vit-base-beans/resolve/main/bean_rust.jpeg
    example_title: Bean Rust
base_model: google/vit-base-patch16-224-in21k
model-index:
  - name: vit-base-beans
    results:
      - task:
          type: image-classification
          name: Image Classification
        dataset:
          name: beans
          type: beans
          args: default
        metrics:
          - type: accuracy
            value: 0.9774436090225563
            name: Accuracy
      - task:
          type: image-classification
          name: Image Classification
        dataset:
          name: beans
          type: beans
          config: default
          split: test
        metrics:
          - type: accuracy
            value: 0.9453125
            name: Accuracy
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNzE4OTNkMmIwZDJhNmEzZGM2NzcxMWMyODhlM2NiM2FkY2Y2ZDdhNzUwMTdhMDdhNDg5NjA0MGNlYzYyYzY0NCIsInZlcnNpb24iOjF9.wwUmRnAJskyiz_MGOwaG5MkX_Q6is5ZqKIuCEo3i3QLCAwIEeZsodGALhm_DBE0P0BMUWCk8SJSvVTADJceQAA
          - type: precision
            value: 0.9453325082933705
            name: Precision Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjE4ODc1OTM2MGIwMTM4M2QzNGJjMDJiZjExNDY3NzUxZWYxOTY3MDk1YzkwZmNmMjc3YWYxYzQ5ZDlhMDBhNiIsInZlcnNpb24iOjF9.7K8IHLSDwCeyA7RdUaLRCrN2sQnXphP3unQnDmJCDg_xURbOMWn7IdufsV8q_qjcDVCy7OwsffnYL9xw8KOmCw
          - type: precision
            value: 0.9453125
            name: Precision Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTVkYjQ4NTUzYTM0ZGMwOThkOTBjZWQ3MTJlMzIyMDhlOWMwMjUzYTg1NDcwYTcyY2QzOGM0MzY3NDE1NzU0YSIsInZlcnNpb24iOjF9._HCFVMp2DxiLhgJWadBKwDIptnLxAdaok_yK2Qsl9kxTFoWid8Cg0HI6SYsIL1WmEXhW1SwePuJFRAzOPQedCA
          - type: precision
            value: 0.9452605321507761
            name: Precision Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMmU2ZWY0OGU2MDBjNjQ4NzE0NjFmYWI1NTVmZDRjNDRiNGI2ZWNkOTYzMmJhZjljYzkzZjRmZjJiYzRkNGY5NCIsInZlcnNpb24iOjF9.WWilSaL_XaubBI519uG0CtoAR5ASl1KVAzJEqfz4yUAn0AG5p6vRnky82f7cHHoFv9ZLhKjQs8HJPG5hqNV1CA
          - type: recall
            value: 0.945736434108527
            name: Recall Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTJhOTBkYzAwNzJlZWFiNzZkNDg1ZTU0YTY2ODRhODRmNzFiYTM0ODcxZmU3MjlkNzBlNjM1NTZjOWMyZjdlOSIsInZlcnNpb24iOjF9.7KPVpzAxAd_70p5jJMDxQm6dwEQ_Ln3xhPFx6IfamJ8u8qFAe9vFPuLddz8w4W3keCYAaxC-5Y13_jLHpRv_BA
          - type: recall
            value: 0.9453125
            name: Recall Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiM2IwZmU0YmYyMDZjNGQ3MjBjNmU0NDEzNDY3ZjQ0Yjc4NmM1NWJhMThjY2Y5NTY0NzJkYTRlNGY1YmExOGQ4MyIsInZlcnNpb24iOjF9.f3ZBu_rNCViY3Uif9qBgDn5XhjfZ_qAlkCle1kANcOUmeAr6AiHn2IHe0XYC6XBfL64N-lK45LlYHX82bF-PAw
          - type: recall
            value: 0.9453125
            name: Recall Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTdhMzQzY2E5ODJkZGM2NjI4MTliYzQyMzdhOTcwNGMwYmJmNjE2MTMyZTI1NmNkZTU1OGY2NGUyMTAwNTNjYiIsInZlcnNpb24iOjF9.EUo_jYaX8Xxo_DPtljm91_4cjDz2_Vvwb-aC9sQiokizxLi7ydSKGQyBn2rwSCEhdV3Bgoljkozru0zy5hPBCg
          - type: f1
            value: 0.9451827242524917
            name: F1 Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDUyYzcwOWU0OGJkNGQ4NjAzNmIwZTU2MWNjMmUwZmMyOTliMTBkOTM5MDRiYzkyOGI1YTQxMzU0ODMxM2E1YiIsInZlcnNpb24iOjF9.cA70lp192tqDNjDoXoYaDpN3oOH_FdD9UDCpwHfoZxUlT5bFikeeX6joaJc8Xq5PTHGg00UVSkCFwFfEFUuNBg
          - type: f1
            value: 0.9453125
            name: F1 Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiY2Y3NzIxZGQyM2ZmNGI2ZDM4YjRkMzEzYzhiYTUyOGFlN2FhMjEyN2YzY2M3ZDFhOTc3MWExOWFlMWFiOTZjNyIsInZlcnNpb24iOjF9.ZIM35jCeGH8S38w-DLTPWRXWZIHY5lCw8W_TO4CIwNTceU2iAjrdZph4EbtXnmbJYJXVtbEWm5Up4-ltVEGGBQ
          - type: f1
            value: 0.944936150332226
            name: F1 Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzFjZDhlNGE4N2ZhOWVmMzBjNzMxMWQxNGZiYjlkODhkNGU1YmY2YTQ2NzJmOTk4ZWY5MzUzNzI5NmMzOWVjYyIsInZlcnNpb24iOjF9.Uz0c_zd8SZKAF1B4Z9NN9_klaTUNwi9u0fIzkeVSE0ah12wIJVpTmy-uukS-0vvgpvQ3ogxEfgXi97vfBQcNAA
          - type: loss
            value: 0.26030588150024414
            name: loss
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjBkNzFiNzIwYjMyMWNhYWM4MzIyMzc1MzNlNDcxZTg3ZDcxNGUxZDg0MTgzYThlMGVjNzI1NDlhYTJjZDJkZCIsInZlcnNpb24iOjF9.VWvtgfJd1-BoaXofW4MhVK6_1dkLHgXKirSRXsfBUdkMkhRymcAai7tku35tNfqDpUJpqJHN0s56x7FbNbxoBQ

vit-base-beans

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

  • Loss: 0.0942
  • Accuracy: 0.9774

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: 2e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 1337
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5.0

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.2809 1.0 130 0.2287 0.9699
0.1097 2.0 260 0.1676 0.9624
0.1027 3.0 390 0.0942 0.9774
0.0923 4.0 520 0.1104 0.9699
0.1726 5.0 650 0.1030 0.9699

Framework versions

  • Transformers 4.10.0.dev0
  • Pytorch 1.9.0+cu102
  • Datasets 1.11.1.dev0
  • Tokenizers 0.10.3