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-MM_Classification
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: 0.8947939262472885
swin-tiny-patch4-window7-224-MM_Classification
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: 0.2758
- Accuracy: 0.8948
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: 128
- eval_batch_size: 128
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 512
- 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 |
|---|---|---|---|---|
| 1.0041 | 0.9846 | 16 | 0.6399 | 0.7082 |
| 0.4441 | 1.9692 | 32 | 0.3671 | 0.8688 |
| 0.3563 | 2.9538 | 48 | 0.3454 | 0.8688 |
| 0.3071 | 4.0 | 65 | 0.3100 | 0.8861 |
| 0.2933 | 4.9846 | 81 | 0.2900 | 0.8894 |
| 0.2841 | 5.9692 | 97 | 0.2917 | 0.8829 |
| 0.2715 | 6.9538 | 113 | 0.2846 | 0.8894 |
| 0.2564 | 8.0 | 130 | 0.2835 | 0.8926 |
| 0.2639 | 8.9846 | 146 | 0.2799 | 0.8926 |
| 0.2505 | 9.8462 | 160 | 0.2758 | 0.8948 |
Framework versions
- Transformers 4.43.3
- Pytorch 1.13.1+cu117
- Datasets 2.20.0
- Tokenizers 0.19.1