metadata
license: apache-2.0
base_model: microsoft/swin-large-patch4-window7-224-in22k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: Boya2_SGD_1e3_20Epoch_Swin-large-224_fold1
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.43978052126200273
Boya2_SGD_1e3_20Epoch_Swin-large-224_fold1
This model is a fine-tuned version of microsoft/swin-large-patch4-window7-224-in22k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.7177
- Accuracy: 0.4398
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: 0.001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.5254 | 1.0 | 914 | 2.5193 | 0.2337 |
| 2.2335 | 2.0 | 1828 | 2.2973 | 0.2768 |
| 2.1501 | 3.0 | 2742 | 2.1851 | 0.2985 |
| 2.0837 | 4.0 | 3656 | 2.0892 | 0.3210 |
| 2.023 | 5.0 | 4570 | 2.0285 | 0.3427 |
| 2.1197 | 6.0 | 5484 | 1.9778 | 0.3567 |
| 1.8735 | 7.0 | 6398 | 1.9315 | 0.3712 |
| 1.9425 | 8.0 | 7312 | 1.8942 | 0.3855 |
| 1.7959 | 9.0 | 8226 | 1.8616 | 0.3975 |
| 1.8811 | 10.0 | 9140 | 1.8352 | 0.4102 |
| 1.7687 | 11.0 | 10054 | 1.8101 | 0.4129 |
| 1.745 | 12.0 | 10968 | 1.7884 | 0.4184 |
| 1.6926 | 13.0 | 11882 | 1.7712 | 0.4241 |
| 1.8703 | 14.0 | 12796 | 1.7556 | 0.4285 |
| 1.799 | 15.0 | 13710 | 1.7425 | 0.4321 |
| 1.7167 | 16.0 | 14624 | 1.7343 | 0.4337 |
| 1.8017 | 17.0 | 15538 | 1.7266 | 0.4362 |
| 1.7314 | 18.0 | 16452 | 1.7220 | 0.4387 |
| 1.8866 | 19.0 | 17366 | 1.7190 | 0.4398 |
| 1.8724 | 20.0 | 18280 | 1.7177 | 0.4398 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.1+cu121
- Datasets 2.21.0
- Tokenizers 0.13.2