metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: blurred_faces
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: faces_resnet
split: validation
args: faces_resnet
metrics:
- name: Accuracy
type: accuracy
value: 0.9964317573595004
blurred_faces
This model is a fine-tuned version of microsoft/resnet-50 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0414
- Accuracy: 0.9964
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.514 | 1.0 | 144 | 0.4884 | 0.9358 |
| 0.242 | 2.0 | 288 | 0.1377 | 0.9893 |
| 0.1592 | 2.99 | 432 | 0.0736 | 0.9902 |
| 0.0956 | 4.0 | 577 | 0.0488 | 0.9955 |
| 0.1734 | 4.99 | 720 | 0.0414 | 0.9964 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 1.13.0
- Datasets 2.10.1
- Tokenizers 0.11.0