|
--- |
|
library_name: transformers |
|
base_model: google/mobilenet_v2_1.0_224 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: mobilenet_v2_1.0_224-finetuned-papsmear |
|
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: 0.8676470588235294 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# mobilenet_v2_1.0_224-finetuned-papsmear |
|
|
|
This model is a fine-tuned version of [google/mobilenet_v2_1.0_224](https://huggingface.co/google/mobilenet_v2_1.0_224) on the imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4698 |
|
- Accuracy: 0.8676 |
|
|
|
## 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: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 60 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-------:|:----:|:---------------:|:--------:| |
|
| 1.7932 | 0.9935 | 38 | 1.7607 | 0.25 | |
|
| 1.6542 | 1.9869 | 76 | 1.5736 | 0.3971 | |
|
| 1.4692 | 2.9804 | 114 | 1.4805 | 0.3676 | |
|
| 1.2759 | 4.0 | 153 | 1.2177 | 0.5809 | |
|
| 1.1521 | 4.9935 | 191 | 1.0727 | 0.6471 | |
|
| 1.078 | 5.9869 | 229 | 0.9996 | 0.6176 | |
|
| 1.0235 | 6.9804 | 267 | 0.8680 | 0.7059 | |
|
| 0.9554 | 8.0 | 306 | 0.9273 | 0.6397 | |
|
| 0.7437 | 8.9935 | 344 | 0.7389 | 0.7059 | |
|
| 0.7876 | 9.9869 | 382 | 0.6774 | 0.7426 | |
|
| 0.7698 | 10.9804 | 420 | 0.6569 | 0.7206 | |
|
| 0.7597 | 12.0 | 459 | 0.6758 | 0.7574 | |
|
| 0.6114 | 12.9935 | 497 | 0.8279 | 0.7132 | |
|
| 0.6847 | 13.9869 | 535 | 0.7505 | 0.7132 | |
|
| 0.5902 | 14.9804 | 573 | 0.7919 | 0.6691 | |
|
| 0.629 | 16.0 | 612 | 0.6117 | 0.7868 | |
|
| 0.5071 | 16.9935 | 650 | 0.6048 | 0.7353 | |
|
| 0.5453 | 17.9869 | 688 | 0.8086 | 0.7279 | |
|
| 0.5071 | 18.9804 | 726 | 0.7835 | 0.7059 | |
|
| 0.5328 | 20.0 | 765 | 0.6139 | 0.75 | |
|
| 0.5053 | 20.9935 | 803 | 0.5981 | 0.7868 | |
|
| 0.4436 | 21.9869 | 841 | 0.5219 | 0.8015 | |
|
| 0.5025 | 22.9804 | 879 | 0.4959 | 0.8088 | |
|
| 0.4984 | 24.0 | 918 | 0.5701 | 0.7794 | |
|
| 0.4655 | 24.9935 | 956 | 0.7179 | 0.7206 | |
|
| 0.3848 | 25.9869 | 994 | 0.5075 | 0.8088 | |
|
| 0.3824 | 26.9804 | 1032 | 0.6645 | 0.7426 | |
|
| 0.4901 | 28.0 | 1071 | 0.7288 | 0.6985 | |
|
| 0.397 | 28.9935 | 1109 | 0.7251 | 0.7279 | |
|
| 0.3818 | 29.9869 | 1147 | 0.6250 | 0.7941 | |
|
| 0.3412 | 30.9804 | 1185 | 0.7065 | 0.7279 | |
|
| 0.3627 | 32.0 | 1224 | 0.6877 | 0.7426 | |
|
| 0.3557 | 32.9935 | 1262 | 0.4245 | 0.8529 | |
|
| 0.441 | 33.9869 | 1300 | 0.6974 | 0.75 | |
|
| 0.3036 | 34.9804 | 1338 | 0.6458 | 0.7426 | |
|
| 0.3213 | 36.0 | 1377 | 0.5579 | 0.7941 | |
|
| 0.402 | 36.9935 | 1415 | 0.4578 | 0.8382 | |
|
| 0.2897 | 37.9869 | 1453 | 0.5369 | 0.7868 | |
|
| 0.348 | 38.9804 | 1491 | 0.6819 | 0.7941 | |
|
| 0.3929 | 40.0 | 1530 | 0.5810 | 0.7868 | |
|
| 0.3173 | 40.9935 | 1568 | 0.7875 | 0.7426 | |
|
| 0.3499 | 41.9869 | 1606 | 0.5051 | 0.8015 | |
|
| 0.3053 | 42.9804 | 1644 | 0.7510 | 0.7426 | |
|
| 0.4109 | 44.0 | 1683 | 0.6529 | 0.75 | |
|
| 0.3846 | 44.9935 | 1721 | 0.9615 | 0.7132 | |
|
| 0.3222 | 45.9869 | 1759 | 0.8889 | 0.6691 | |
|
| 0.3293 | 46.9804 | 1797 | 0.4698 | 0.8676 | |
|
| 0.293 | 48.0 | 1836 | 0.5996 | 0.8015 | |
|
| 0.2363 | 48.9935 | 1874 | 0.5007 | 0.8309 | |
|
| 0.2811 | 49.9869 | 1912 | 0.6748 | 0.7941 | |
|
| 0.2403 | 50.9804 | 1950 | 0.6595 | 0.7941 | |
|
| 0.2553 | 52.0 | 1989 | 0.5987 | 0.7794 | |
|
| 0.2959 | 52.9935 | 2027 | 0.5459 | 0.8235 | |
|
| 0.3066 | 53.9869 | 2065 | 0.6198 | 0.7868 | |
|
| 0.2981 | 54.9804 | 2103 | 0.4886 | 0.8309 | |
|
| 0.2658 | 56.0 | 2142 | 0.6422 | 0.7794 | |
|
| 0.2371 | 56.9935 | 2180 | 0.5000 | 0.8382 | |
|
| 0.2331 | 57.9869 | 2218 | 0.8854 | 0.7132 | |
|
| 0.2777 | 58.9804 | 2256 | 0.6190 | 0.8015 | |
|
| 0.3047 | 59.6078 | 2280 | 0.6048 | 0.7647 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.0 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
