swin-tiny-patch4-window7-224-finetuned-eurosat

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

  • Loss: 0.0271
  • Accuracy: 0.9967

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: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 15

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.0898 1.0 327 0.0707 0.9757
0.0221 2.0 654 0.0278 0.9920
0.06 3.0 981 0.0345 0.9913
0.0094 4.0 1309 0.0300 0.9947
0.0004 5.0 1636 0.0398 0.9942
0.0035 6.0 1963 0.0136 0.9975
0.0246 7.0 2290 0.0339 0.9940
0.0012 8.0 2618 0.0316 0.9958
0.0 9.0 2945 0.0302 0.9964
0.0 10.0 3272 0.0201 0.9973
0.0003 11.0 3599 0.0222 0.9955
0.0 12.0 3927 0.0218 0.9962
0.0001 13.0 4254 0.0293 0.9962
0.0002 14.0 4581 0.0272 0.9962
0.0 14.99 4905 0.0271 0.9967

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.15.0
  • Tokenizers 0.15.0
Downloads last month
83
Safetensors
Model size
27.5M params
Tensor type
I64
·
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for andrecastro/swin-tiny-patch4-window7-224-finetuned-eurosat

Finetuned
(483)
this model

Evaluation results