metadata
license: apache-2.0
base_model: microsoft/swinv2-tiny-patch4-window8-256
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: swinv2-tiny-patch4-window8-256
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: 0.83
swinv2-tiny-patch4-window8-256
This model is a fine-tuned version of microsoft/swinv2-tiny-patch4-window8-256 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.7288
- Accuracy: 0.83
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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.6146 | 1.0 | 50 | 1.4437 | 0.49 |
| 1.2101 | 2.0 | 100 | 1.0506 | 0.665 |
| 0.8151 | 3.0 | 150 | 0.8444 | 0.745 |
| 0.4959 | 4.0 | 200 | 0.7774 | 0.805 |
| 0.4246 | 5.0 | 250 | 0.7304 | 0.825 |
| 0.3254 | 6.0 | 300 | 0.7692 | 0.805 |
| 0.2017 | 7.0 | 350 | 0.7213 | 0.815 |
| 0.2081 | 8.0 | 400 | 0.7288 | 0.83 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1