Downloads · 30 days
10
1% of all-time downloads
trained-age
crangana/trained-age
trained-age is a image classification model from crangana. Use it when you need a label for an image. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
796
Public
Repo size
189 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin94.4 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- resnet
- Access
- Public
- Created
- Oct 4, 2023
- Updated
- Oct 4, 2023
- SHA
- 57a70897
Base models
Datasets
Model card
From the Hugging Face model README
<!-- 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. -->
trained-age
This model is a fine-tuned version of microsoft/resnet-50 on the fair_face dataset. It achieves the following results on the evaluation set:
- Loss: 1.1340
- Accuracy: 0.5164
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.3347 | 0.18 | 1000 | 1.3819 | 0.4296 |
| 1.3071 | 0.37 | 2000 | 1.2799 | 0.4642 |
| 1.297 | 0.55 | 3000 | 1.2503 | 0.4721 |
| 1.3121 | 0.74 | 4000 | 1.1661 | 0.4995 |
| 1.1806 | 0.92 | 5000 | 1.1137 | 0.5240 |
| 1.0839 | 1.11 | 6000 | 1.1340 | 0.5164 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0
- Task
- Image Classification
- Library
- transformers
- Type
- resnet
- License
- apache-2.0
- Created
- Oct 4, 2023
- Updated
- Oct 4, 2023