metadata
license: apache-2.0
base_model: microsoft/swinv2-base-patch4-window12-192-22k
tags:
- generated_from_trainer
datasets:
- p1atdev/pvc
metrics:
- accuracy
model-index:
- name: pvc-quality-swinv2-base
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.5317220543806647
library_name: transformers
pvc-quality-swinv2-base
This model is a fine-tuned version of microsoft/swinv2-base-patch4-window12-192-22k on the pvc figure images dataset. It achieves the following results on the evaluation set:
- Loss: 1.2396
- Accuracy: 0.5317
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: 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: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.7254 | 0.98 | 39 | 1.4826 | 0.4109 |
| 1.3316 | 1.99 | 79 | 1.2177 | 0.5136 |
| 1.0864 | 2.99 | 119 | 1.3006 | 0.4653 |
| 0.8572 | 4.0 | 159 | 1.2090 | 0.5015 |
| 0.7466 | 4.98 | 198 | 1.2150 | 0.5378 |
| 0.5986 | 5.99 | 238 | 1.4600 | 0.4955 |
| 0.4784 | 6.99 | 278 | 1.4131 | 0.5196 |
| 0.3525 | 8.0 | 318 | 1.5256 | 0.4985 |
| 0.3472 | 8.98 | 357 | 1.3883 | 0.5166 |
| 0.3281 | 9.81 | 390 | 1.5012 | 0.4955 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0