metadata
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: swin-tiny-patch4-window7-224-finetuned-sealv1
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: 0.9119804400977995
swin-tiny-patch4-window7-224-finetuned-sealv1
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: 0.2553
- Accuracy: 0.9120
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 |
---|---|---|---|---|
1.1068 | 0.95 | 14 | 0.6518 | 0.7066 |
0.4912 | 1.97 | 29 | 0.4668 | 0.8435 |
0.2749 | 2.98 | 44 | 0.4127 | 0.8704 |
0.3189 | 4.0 | 59 | 0.3626 | 0.8875 |
0.2226 | 4.95 | 73 | 0.2638 | 0.9046 |
0.2394 | 5.97 | 88 | 0.3584 | 0.8802 |
0.2241 | 6.98 | 103 | 0.2821 | 0.9046 |
0.1815 | 8.0 | 118 | 0.2138 | 0.9218 |
0.1862 | 8.95 | 132 | 0.2738 | 0.9046 |
0.1942 | 9.49 | 140 | 0.2553 | 0.9120 |
Framework versions
- Transformers 4.38.2
- Pytorch 1.10.2+cu113
- Datasets 2.18.0
- Tokenizers 0.15.2