metadata
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: swin-tiny-patch4-window7-224-Mid-NonMidMarket-Classification
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: 0.9172749391727494
swin-tiny-patch4-window7-224-Mid-NonMidMarket-Classification
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: 0.2099
- Accuracy: 0.9173
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2558 | 0.9836 | 30 | 0.2284 | 0.9124 |
| 0.2409 | 2.0 | 61 | 0.2099 | 0.9173 |
| 0.2151 | 2.9836 | 91 | 0.2273 | 0.9051 |
| 0.2085 | 4.0 | 122 | 0.2338 | 0.9002 |
| 0.1793 | 4.9836 | 152 | 0.2289 | 0.9051 |
| 0.1817 | 6.0 | 183 | 0.2174 | 0.9075 |
| 0.1852 | 6.9836 | 213 | 0.2230 | 0.9002 |
| 0.1739 | 8.0 | 244 | 0.2171 | 0.9100 |
| 0.1569 | 8.9836 | 274 | 0.2114 | 0.9148 |
| 0.1589 | 9.8361 | 300 | 0.2154 | 0.9100 |
Framework versions
- Transformers 4.42.3
- Pytorch 1.12.1+cu113
- Datasets 2.19.2
- Tokenizers 0.19.1