metadata
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
- recall
- precision
- f1
model-index:
- name: FFPP-Raw_1FPS_faces-expand-40-aligned_metric-acc-precision-recall-f1
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: 0.8064887989445775
- name: Recall
type: recall
value: 0.599275070479259
- name: Precision
type: precision
value: 0.26912642430819317
- name: F1
type: f1
value: 0.37144283574638043
FFPP-Raw_1FPS_faces-expand-40-aligned_metric-acc-precision-recall-f1
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: 0.4464
- Accuracy: 0.8065
- Recall: 0.5993
- Precision: 0.2691
- F1: 0.3714
- Roc Auc: 0.8135
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Recall | Precision | F1 | Roc Auc |
|---|---|---|---|---|---|---|---|---|
| 0.1821 | 1.0 | 1348 | 0.1286 | 0.9464 | 0.8533 | 0.8953 | 0.8738 | 0.9858 |
| 0.1333 | 2.0 | 2696 | 0.0715 | 0.9725 | 0.9129 | 0.9586 | 0.9352 | 0.9960 |
| 0.0809 | 3.0 | 4044 | 0.0520 | 0.9804 | 0.9344 | 0.9743 | 0.9539 | 0.9980 |
Framework versions
- Transformers 4.39.2
- Pytorch 2.2.2
- Datasets 2.18.0
- Tokenizers 0.15.2