metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: swin-tiny-patch4-window7-224-finetuned-eurosat
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 1
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: 0.0600
- Accuracy: 1.0
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: 40
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 1 | 1.4318 | 0.8 |
| No log | 2.0 | 2 | 1.3863 | 0.8 |
| No log | 3.0 | 3 | 1.2880 | 0.8 |
| No log | 4.0 | 4 | 1.1589 | 0.8 |
| No log | 5.0 | 5 | 0.9954 | 0.8 |
| No log | 6.0 | 6 | 0.8942 | 0.8 |
| No log | 7.0 | 7 | 0.8269 | 0.8 |
| No log | 8.0 | 8 | 0.7702 | 0.8 |
| No log | 9.0 | 9 | 0.7138 | 1.0 |
| No log | 10.0 | 10 | 0.6602 | 1.0 |
| No log | 11.0 | 11 | 0.6255 | 1.0 |
| No log | 12.0 | 12 | 0.5900 | 1.0 |
| No log | 13.0 | 13 | 0.5367 | 1.0 |
| No log | 14.0 | 14 | 0.4790 | 1.0 |
| No log | 15.0 | 15 | 0.4158 | 1.0 |
| No log | 16.0 | 16 | 0.3573 | 1.0 |
| No log | 17.0 | 17 | 0.2964 | 1.0 |
| No log | 18.0 | 18 | 0.2439 | 1.0 |
| No log | 19.0 | 19 | 0.2028 | 1.0 |
| 0.5248 | 20.0 | 20 | 0.1671 | 1.0 |
| 0.5248 | 21.0 | 21 | 0.1399 | 1.0 |
| 0.5248 | 22.0 | 22 | 0.1182 | 1.0 |
| 0.5248 | 23.0 | 23 | 0.1013 | 1.0 |
| 0.5248 | 24.0 | 24 | 0.0897 | 1.0 |
| 0.5248 | 25.0 | 25 | 0.0824 | 1.0 |
| 0.5248 | 26.0 | 26 | 0.0769 | 1.0 |
| 0.5248 | 27.0 | 27 | 0.0721 | 1.0 |
| 0.5248 | 28.0 | 28 | 0.0701 | 1.0 |
| 0.5248 | 29.0 | 29 | 0.0697 | 1.0 |
| 0.5248 | 30.0 | 30 | 0.0693 | 1.0 |
| 0.5248 | 31.0 | 31 | 0.0672 | 1.0 |
| 0.5248 | 32.0 | 32 | 0.0646 | 1.0 |
| 0.5248 | 33.0 | 33 | 0.0633 | 1.0 |
| 0.5248 | 34.0 | 34 | 0.0628 | 1.0 |
| 0.5248 | 35.0 | 35 | 0.0626 | 1.0 |
| 0.5248 | 36.0 | 36 | 0.0626 | 1.0 |
| 0.5248 | 37.0 | 37 | 0.0617 | 1.0 |
| 0.5248 | 38.0 | 38 | 0.0608 | 1.0 |
| 0.5248 | 39.0 | 39 | 0.0603 | 1.0 |
| 0.2241 | 40.0 | 40 | 0.0600 | 1.0 |
Framework versions
- Transformers 4.21.2
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1