metadata
license: apache-2.0
base_model: microsoft/swin-base-patch4-window7-224-in22k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- f1
model-index:
- name: swin-base-patch4-window7-224-in22k
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: F1
type: f1
value: 0.976218332192814
swin-base-patch4-window7-224-in22k
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: 0.0117
- F1: 0.9762
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 | F1 |
|---|---|---|---|---|
| 0.0575 | 0.99 | 50 | 0.0560 | 0.9257 |
| 0.0561 | 2.0 | 101 | 0.0359 | 0.9475 |
| 0.027 | 2.99 | 151 | 0.0212 | 0.9643 |
| 0.0236 | 4.0 | 202 | 0.0145 | 0.9737 |
| 0.0256 | 4.99 | 252 | 0.0269 | 0.9503 |
| 0.0226 | 6.0 | 303 | 0.0123 | 0.9762 |
| 0.0265 | 6.99 | 353 | 0.0135 | 0.9731 |
| 0.0168 | 8.0 | 404 | 0.0098 | 0.9824 |
| 0.0074 | 8.99 | 454 | 0.0172 | 0.9700 |
| 0.0125 | 9.9 | 500 | 0.0117 | 0.9762 |
Framework versions
- Transformers 4.37.2
- Pytorch 1.12.1+cu102
- Datasets 2.16.1
- Tokenizers 0.15.1