Downloads · 30 days
11
12% of all-time downloads
ConvnextV2-tiny
vuongnhathien/ConvnextV2-tiny
ConvnextV2-tiny is a image classification model from vuongnhathien. 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
92
Public
Parameters
27.9M
1.8 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors112 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- convnextv2
- Access
- Public
- Created
- May 21, 2024
- Updated
- May 21, 2024
- SHA
- b54e89fd
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. -->
ConvnextV2-base
This model is a fine-tuned version of facebook/convnextv2-tiny-22k-384 on the vuongnhathien/30VNFoods dataset. It achieves the following results on the evaluation set:
- Loss: 0.4650
- Accuracy: 0.9192
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: 0.0003
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5453 | 1.0 | 550 | 0.5385 | 0.8465 |
| 0.3201 | 2.0 | 1100 | 0.5494 | 0.8465 |
| 0.1818 | 3.0 | 1650 | 0.4973 | 0.8732 |
| 0.0974 | 4.0 | 2200 | 0.5644 | 0.8652 |
| 0.059 | 5.0 | 2750 | 0.5624 | 0.8891 |
| 0.0371 | 6.0 | 3300 | 0.6428 | 0.8755 |
| 0.0118 | 7.0 | 3850 | 0.5426 | 0.9026 |
| 0.0169 | 8.0 | 4400 | 0.4927 | 0.9161 |
| 0.0103 | 9.0 | 4950 | 0.5011 | 0.9105 |
| 0.0017 | 10.0 | 5500 | 0.4820 | 0.9165 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
- Task
- Image Classification
- Library
- transformers
- Type
- convnextv2
- License
- apache-2.0
- Created
- May 21, 2024
- Updated
- May 21, 2024