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-ve-U13-b-12
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: 0.5434782608695652
swin-tiny-patch4-window7-224-ve-U13-b-12
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: 0.9160
- Accuracy: 0.5435
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: 12
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
No log | 1.0 | 8 | 1.3788 | 0.4348 |
1.3828 | 2.0 | 16 | 1.3084 | 0.5 |
1.2902 | 3.0 | 24 | 1.1908 | 0.4783 |
1.1227 | 4.0 | 32 | 1.1055 | 0.4130 |
0.9806 | 5.0 | 40 | 1.0173 | 0.5217 |
0.9806 | 6.0 | 48 | 0.9396 | 0.5217 |
0.8629 | 7.0 | 56 | 0.9529 | 0.5 |
0.7707 | 8.0 | 64 | 0.9449 | 0.5217 |
0.7411 | 9.0 | 72 | 0.9160 | 0.5435 |
0.671 | 10.0 | 80 | 0.9073 | 0.5435 |
0.671 | 11.0 | 88 | 0.9192 | 0.5435 |
0.6501 | 12.0 | 96 | 0.9456 | 0.5 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0