|
--- |
|
license: apache-2.0 |
|
base_model: microsoft/swin-base-patch4-window7-224-in22k |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: swin-base-patch4-window7-224-in22k-finetuned-cifar10 |
|
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: 0.9858 |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# swin-base-patch4-window7-224-in22k-finetuned-cifar10 |
|
|
|
This model is a fine-tuned version of [microsoft/swin-base-patch4-window7-224-in22k](https://huggingface.co./microsoft/swin-base-patch4-window7-224-in22k) on the imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0414 |
|
- Accuracy: 0.9858 |
|
|
|
## 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: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 2.303 | 0.03 | 10 | 2.1672 | 0.2334 | |
|
| 2.0158 | 0.06 | 20 | 1.6672 | 0.657 | |
|
| 1.4855 | 0.09 | 30 | 0.8292 | 0.8704 | |
|
| 0.7451 | 0.11 | 40 | 0.2578 | 0.93 | |
|
| 0.5618 | 0.14 | 50 | 0.1476 | 0.962 | |
|
| 0.4545 | 0.17 | 60 | 0.1248 | 0.9642 | |
|
| 0.4587 | 0.2 | 70 | 0.0941 | 0.9748 | |
|
| 0.3911 | 0.23 | 80 | 0.0944 | 0.9712 | |
|
| 0.3839 | 0.26 | 90 | 0.0848 | 0.9756 | |
|
| 0.3864 | 0.28 | 100 | 0.0744 | 0.978 | |
|
| 0.3141 | 0.31 | 110 | 0.0673 | 0.98 | |
|
| 0.3764 | 0.34 | 120 | 0.0706 | 0.9764 | |
|
| 0.3003 | 0.37 | 130 | 0.0600 | 0.984 | |
|
| 0.3566 | 0.4 | 140 | 0.0562 | 0.9826 | |
|
| 0.2855 | 0.43 | 150 | 0.0567 | 0.9816 | |
|
| 0.3351 | 0.45 | 160 | 0.0543 | 0.9828 | |
|
| 0.2977 | 0.48 | 170 | 0.0568 | 0.9798 | |
|
| 0.2924 | 0.51 | 180 | 0.0577 | 0.9804 | |
|
| 0.2884 | 0.54 | 190 | 0.0551 | 0.983 | |
|
| 0.3067 | 0.57 | 200 | 0.0487 | 0.983 | |
|
| 0.3159 | 0.6 | 210 | 0.0513 | 0.984 | |
|
| 0.2795 | 0.63 | 220 | 0.0460 | 0.9846 | |
|
| 0.3113 | 0.65 | 230 | 0.0495 | 0.9832 | |
|
| 0.2882 | 0.68 | 240 | 0.0475 | 0.9838 | |
|
| 0.263 | 0.71 | 250 | 0.0449 | 0.9854 | |
|
| 0.2686 | 0.74 | 260 | 0.0510 | 0.9826 | |
|
| 0.2705 | 0.77 | 270 | 0.0483 | 0.9846 | |
|
| 0.2807 | 0.8 | 280 | 0.0430 | 0.9854 | |
|
| 0.2583 | 0.82 | 290 | 0.0452 | 0.9858 | |
|
| 0.2346 | 0.85 | 300 | 0.0435 | 0.9858 | |
|
| 0.2294 | 0.88 | 310 | 0.0434 | 0.986 | |
|
| 0.2608 | 0.91 | 320 | 0.0433 | 0.986 | |
|
| 0.2642 | 0.94 | 330 | 0.0425 | 0.9866 | |
|
| 0.2781 | 0.97 | 340 | 0.0417 | 0.986 | |
|
| 0.247 | 1.0 | 350 | 0.0414 | 0.9858 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.0 |
|
- Pytorch 2.1.1 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|
