|
--- |
|
license: apache-2.0 |
|
base_model: microsoft/swin-tiny-patch4-window7-224 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: segformer-class-classWeights-augmentation |
|
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: 0.9655172413793104 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# segformer-class-classWeights-augmentation |
|
|
|
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0355 |
|
- Accuracy: 0.9655 |
|
|
|
## 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: 10 |
|
- eval_batch_size: 10 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 40 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| No log | 0.89 | 6 | 1.0977 | 0.5517 | |
|
| 1.0215 | 1.93 | 13 | 0.6858 | 0.7931 | |
|
| 0.6364 | 2.96 | 20 | 0.9383 | 0.6897 | |
|
| 0.6364 | 4.0 | 27 | 0.2391 | 0.9310 | |
|
| 0.2716 | 4.89 | 33 | 0.1767 | 0.8966 | |
|
| 0.2295 | 5.93 | 40 | 0.2729 | 0.9310 | |
|
| 0.2295 | 6.96 | 47 | 0.1429 | 0.9655 | |
|
| 0.1311 | 8.0 | 54 | 0.1929 | 0.9655 | |
|
| 0.1503 | 8.89 | 60 | 0.1718 | 0.9655 | |
|
| 0.1503 | 9.93 | 67 | 0.1631 | 0.9655 | |
|
| 0.1554 | 10.96 | 74 | 0.2690 | 0.9655 | |
|
| 0.1157 | 12.0 | 81 | 0.1331 | 0.9655 | |
|
| 0.1157 | 12.89 | 87 | 0.0512 | 0.9655 | |
|
| 0.1093 | 13.93 | 94 | 0.0273 | 1.0 | |
|
| 0.134 | 14.96 | 101 | 0.0356 | 0.9655 | |
|
| 0.134 | 16.0 | 108 | 0.0477 | 0.9655 | |
|
| 0.0926 | 16.89 | 114 | 0.0381 | 0.9655 | |
|
| 0.1363 | 17.78 | 120 | 0.0355 | 0.9655 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.13.1 |
|
- Tokenizers 0.13.3 |
|
|
