metadata
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: 0.8620689655172413
segformer-class-classWeights-augmentation
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: 0.4872
- Accuracy: 0.8621
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 1 | 1.1700 | 0.2759 |
| No log | 2.0 | 3 | 1.0351 | 0.3793 |
| No log | 3.0 | 5 | 0.9731 | 0.5172 |
| No log | 4.0 | 6 | 0.9362 | 0.5172 |
| No log | 5.0 | 7 | 0.8890 | 0.5517 |
| No log | 6.0 | 9 | 0.7596 | 0.7586 |
| 0.5024 | 7.0 | 11 | 0.6531 | 0.8621 |
| 0.5024 | 8.0 | 12 | 0.6170 | 0.8621 |
| 0.5024 | 9.0 | 13 | 0.5878 | 0.8966 |
| 0.5024 | 10.0 | 15 | 0.5418 | 0.8621 |
| 0.5024 | 11.0 | 17 | 0.5122 | 0.8621 |
| 0.5024 | 12.0 | 18 | 0.5021 | 0.8621 |
| 0.5024 | 13.0 | 19 | 0.4928 | 0.8621 |
| 0.3117 | 13.33 | 20 | 0.4872 | 0.8621 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3