README.md

metadata

license: apache-2.0
tags:
  - huggingpics
  - image-classification
  - generated_from_trainer
metrics:
  - accuracy
model_index:
  - name: planes-trains-automobiles
    results:
      - task:
          name: Image Classification
          type: image-classification
        metric:
          name: Accuracy
          type: accuracy
          value: 0.9850746268656716
base_model: google/vit-base-patch16-224-in21k

planes-trains-automobiles

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

• Loss: 0.0534
• Accuracy: 0.9851

Model description

Autogenerated by HuggingPics🤗🖼️

Create your own image classifier for anything by running the demo on Google Colab.

Report any issues with the demo at the github repo.

Example Images

automobiles

planes

trains

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: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.0283	1.0	48	0.0434	0.9851
0.0224	2.0	96	0.0548	0.9851
0.0203	3.0	144	0.0445	0.9851
0.0195	4.0	192	0.0534	0.9851

Framework versions

• Transformers 4.9.2
• Pytorch 1.9.0+cu102
• Datasets 1.11.0
• Tokenizers 0.10.3