metadata
license: apache-2.0
base_model: microsoft/swinv2-small-patch4-window8-256
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: swinv2-small-patch4-window8-256-finetuned-eurosat
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: validation
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.7333333333333333
swinv2-small-patch4-window8-256-finetuned-eurosat
This model is a fine-tuned version of microsoft/swinv2-small-patch4-window8-256 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.5868
- Accuracy: 0.7333
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: 0.05
- 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 8 | 1.1951 | 0.2667 |
| 5.0901 | 2.0 | 16 | 1.4301 | 0.7333 |
| 2.785 | 3.0 | 24 | 1.1514 | 0.2667 |
| 0.8599 | 4.0 | 32 | 0.5810 | 0.7333 |
| 0.6058 | 5.0 | 40 | 0.5868 | 0.7333 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3