|
---
|
|
license: apache-2.0
|
|
base_model: microsoft/swinv2-large-patch4-window12-192-22k
|
|
tags:
|
|
- generated_from_trainer
|
|
datasets:
|
|
- imagefolder
|
|
metrics:
|
|
- accuracy
|
|
model-index:
|
|
- name: swinv2-large-patch4-window12-192-22k-baseline
|
|
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: 0.8765432098765432
|
|
---
|
|
|
|
<!-- 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. -->
|
|
|
|
# swinv2-large-patch4-window12-192-22k-baseline
|
|
|
|
This model is a fine-tuned version of [microsoft/swinv2-large-patch4-window12-192-22k](https://huggingface.co/microsoft/swinv2-large-patch4-window12-192-22k) on the imagefolder dataset.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 0.3489
|
|
- Accuracy: 0.8765
|
|
|
|
## 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: 0.0001
|
|
- train_batch_size: 18
|
|
- eval_batch_size: 18
|
|
- seed: 42
|
|
- gradient_accumulation_steps: 2
|
|
- total_train_batch_size: 36
|
|
- 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 |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
|
| 1.1721 | 1.0 | 20 | 0.8152 | 0.7407 |
|
|
| 0.5878 | 2.0 | 40 | 0.4285 | 0.8395 |
|
|
| 0.5201 | 3.0 | 60 | 0.5102 | 0.8148 |
|
|
| 0.3366 | 4.0 | 80 | 0.3463 | 0.8519 |
|
|
| 0.2792 | 5.0 | 100 | 0.4444 | 0.8272 |
|
|
| 0.2807 | 6.0 | 120 | 0.3282 | 0.8765 |
|
|
| 0.1978 | 7.0 | 140 | 0.3047 | 0.8642 |
|
|
| 0.2262 | 8.0 | 160 | 0.4534 | 0.8765 |
|
|
| 0.176 | 9.0 | 180 | 0.3605 | 0.8148 |
|
|
| 0.17 | 10.0 | 200 | 0.4222 | 0.8642 |
|
|
| 0.1445 | 11.0 | 220 | 0.3569 | 0.9012 |
|
|
| 0.128 | 12.0 | 240 | 0.4649 | 0.8642 |
|
|
| 0.1316 | 13.0 | 260 | 0.3848 | 0.8765 |
|
|
| 0.1772 | 14.0 | 280 | 0.4242 | 0.8395 |
|
|
| 0.1087 | 15.0 | 300 | 0.3756 | 0.8889 |
|
|
| 0.0858 | 16.0 | 320 | 0.4190 | 0.8519 |
|
|
| 0.1136 | 17.0 | 340 | 0.4902 | 0.8765 |
|
|
| 0.0425 | 18.0 | 360 | 0.3041 | 0.9012 |
|
|
| 0.07 | 19.0 | 380 | 0.3456 | 0.8889 |
|
|
| 0.0595 | 20.0 | 400 | 0.3489 | 0.8765 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.35.0
|
|
- Pytorch 2.1.1+cu118
|
|
- Datasets 2.14.6
|
|
- Tokenizers 0.14.1
|
|
|
