metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: >-
swin-base-patch4-window7-224-in22k-finetuned_swinv1-all-classes-autotags-latest
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: 0.9544554455445544
swin-base-patch4-window7-224-in22k-finetuned_swinv1-all-classes-autotags-latest
This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224-in22k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1665
- Accuracy: 0.9545
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- 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 |
|---|---|---|---|---|
| 0.8729 | 1.0 | 63 | 0.6445 | 0.7921 |
| 0.4323 | 2.0 | 126 | 0.3358 | 0.8960 |
| 0.3421 | 3.0 | 189 | 0.2650 | 0.9178 |
| 0.198 | 4.0 | 252 | 0.2080 | 0.9327 |
| 0.1239 | 5.0 | 315 | 0.1797 | 0.9446 |
| 0.1053 | 6.0 | 378 | 0.1625 | 0.9525 |
| 0.1109 | 7.0 | 441 | 0.1712 | 0.9505 |
| 0.0411 | 8.0 | 504 | 0.1850 | 0.9436 |
| 0.0615 | 9.0 | 567 | 0.1695 | 0.9554 |
| 0.0407 | 10.0 | 630 | 0.1665 | 0.9545 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1+cu117
- Datasets 2.11.0
- Tokenizers 0.13.2