Downloads · 30 days
0
Dataset1-FastViT
Nicole-M/Dataset1-FastViT
Dataset1-FastViT is a image classification model from Nicole-M. Use it when you need a label for an image. It is set up for fastai.
This model is a fine-tuned version of FastViT on the Mammogram V1 dataset. It achieves the following results on the evaluation set: - Loss: 0.1645 - Accuracy: 0.9517
Access
Public
Updated Aug 26, 2024
Repo size
87.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pkl87.9 MB · 100%
At a glance
- Task
- Image Classification
- Library
- fastai
- Access
- Public
- Created
- Aug 16, 2024
- Updated
- Aug 26, 2024
- SHA
- 1a5f7ada
Base models
Model card
From the Hugging Face model README
This model is a fine-tuned version of FastViT on the Mammogram V1 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1645
- Accuracy: 0.9517
Model description
More information needed
Intended uses & limitations
More information needed
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-04
- train_batch_size: 32
- eval_batch_size: 32
Training and evaluation data
| Training Loss | Epoch | Validation Loss | Accuracy |
|---|---|---|---|
| 0.6094 | 1.0 | 0.6453 | 0.6135 |
| 0.4967 | 2.0 | 0.4347 | 0.8259 |
| 0.3796 | 3.0 | 0.3768 | 0.7799 |
| 0.2927 | 4.0 | 0.3472 | 0.8463 |
| 0.2822 | 5.0 | 0.1645 | 0.9517 |
Framework Versions
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- FastAi
- Task
- Image Classification
- Library
- fastai
- Created
- Aug 16, 2024
- Updated
- Aug 26, 2024