metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- image_folder
metrics:
- accuracy
model-index:
- name: resnet-50-finetuned-FER2013-0.001
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: image_folder
type: image_folder
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.6847311228754528
resnet-50-finetuned-FER2013-0.001
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: 0.9002
- Accuracy: 0.6847
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: 0.001
- 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.4723 | 1.0 | 224 | 1.3382 | 0.4887 |
| 1.2236 | 2.0 | 448 | 1.1090 | 0.5751 |
| 1.1728 | 3.0 | 672 | 1.0262 | 0.6158 |
| 1.1545 | 4.0 | 896 | 0.9717 | 0.6339 |
| 1.0776 | 5.0 | 1120 | 0.9885 | 0.6360 |
| 1.0183 | 6.0 | 1344 | 0.9475 | 0.6560 |
| 0.9856 | 7.0 | 1568 | 0.9114 | 0.6700 |
| 0.953 | 8.0 | 1792 | 0.9074 | 0.6767 |
| 0.9151 | 9.0 | 2016 | 0.9076 | 0.6833 |
| 0.9355 | 10.0 | 2240 | 0.9002 | 0.6847 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1