|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- image_folder |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: resnet-50-finetuned-FER2013-0.003 |
|
results: |
|
- task: |
|
name: Image Classification |
|
type: image-classification |
|
dataset: |
|
name: image_folder |
|
type: image_folder |
|
args: default |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.6971301198105322 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# resnet-50-finetuned-FER2013-0.003 |
|
|
|
This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the image_folder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9036 |
|
- Accuracy: 0.6971 |
|
|
|
## 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: 0.003 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 128 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 15 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 1.4393 | 1.0 | 224 | 1.2746 | 0.5173 | |
|
| 1.2564 | 2.0 | 448 | 1.1456 | 0.5542 | |
|
| 1.218 | 3.0 | 672 | 1.1102 | 0.5816 | |
|
| 1.1919 | 4.0 | 896 | 1.0255 | 0.6151 | |
|
| 1.1222 | 5.0 | 1120 | 1.0257 | 0.6167 | |
|
| 1.0925 | 6.0 | 1344 | 0.9676 | 0.6317 | |
|
| 1.0241 | 7.0 | 1568 | 0.9406 | 0.6510 | |
|
| 1.0015 | 8.0 | 1792 | 0.9465 | 0.6532 | |
|
| 0.987 | 9.0 | 2016 | 0.9002 | 0.6748 | |
|
| 0.9768 | 10.0 | 2240 | 0.9086 | 0.6737 | |
|
| 0.9408 | 11.0 | 2464 | 0.8975 | 0.6793 | |
|
| 0.8907 | 12.0 | 2688 | 0.8966 | 0.6769 | |
|
| 0.8051 | 13.0 | 2912 | 0.9142 | 0.6826 | |
|
| 0.8169 | 14.0 | 3136 | 0.9082 | 0.6870 | |
|
| 0.7729 | 15.0 | 3360 | 0.9036 | 0.6971 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.20.1 |
|
- Pytorch 1.11.0 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.12.1 |
|
|
