Edit model card

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: 0.6650
  • Accuracy: 0.805

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
0.2566 0.9825 14 0.7227 0.74
0.2729 1.9649 28 0.3916 0.815
0.1553 2.9474 42 0.8409 0.75
0.1371 4.0 57 0.3706 0.885
0.1588 4.9825 71 0.8758 0.765
0.1093 5.9649 85 0.6063 0.82
0.102 6.9474 99 0.5308 0.84
0.0713 8.0 114 0.3536 0.88
0.1045 8.9825 128 0.3858 0.875
0.0661 9.8246 140 0.6650 0.805

Framework versions

  • Transformers 4.40.0
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1
Downloads last month
7
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 DouglasBraga/swin-tiny-patch4-window7-224-finetuned-eurosat

Finetuned
(452)
this model

Evaluation results