metadata
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
resnet-50-finetuned-FER2013-0.003
This model is a fine-tuned version of 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