lu5's picture
Model save
d4938b6
|
raw
history blame
2.44 kB
metadata
license: apache-2.0
base_model: microsoft/swinv2-tiny-patch4-window8-256
tags:
  - generated_from_trainer
datasets:
  - food101
metrics:
  - accuracy
model-index:
  - name: swinv2-tiny-patch4-window8-256-finetuned-eurosat
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: food101
          type: food101
          config: default
          split: validation
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8858613861386139

swinv2-tiny-patch4-window8-256-finetuned-eurosat

This model is a fine-tuned version of microsoft/swinv2-tiny-patch4-window8-256 on the food101 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3997
  • Accuracy: 0.8859

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: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
1.8552 1.0 592 1.1245 0.6955
1.2938 2.0 1184 0.6712 0.8131
1.2294 3.0 1776 0.5354 0.8492
1.0199 4.0 2368 0.4958 0.8594
0.9914 5.0 2960 0.4633 0.8678
0.8786 6.0 3552 0.4390 0.8750
0.806 7.0 4144 0.4206 0.8791
0.7506 8.0 4736 0.4093 0.8832
0.7433 9.0 5328 0.4053 0.8841
0.6393 10.0 5920 0.3997 0.8859

Framework versions

  • Transformers 4.32.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.4
  • Tokenizers 0.13.3