Downloads · 30 days
6
1% of all-time downloads
isl-nodel
sakethchalla/isl-nodel
isl-nodel is a image classification model from sakethchalla. 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
573
Public
Repo size
3.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin343 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- vit
- Access
- Public
- Created
- Apr 10, 2023
- Updated
- Apr 10, 2023
- SHA
- 8208104f
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. -->
isl-nodel
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.9554
- Accuracy: 0.7540
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- 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 |
|---|---|---|---|---|
| 2.6213 | 1.0 | 89 | 2.3886 | 0.6128 |
| 1.66 | 2.0 | 178 | 1.5769 | 0.7119 |
| 1.3588 | 3.0 | 267 | 1.3264 | 0.7358 |
| 1.1062 | 4.0 | 356 | 1.1833 | 0.7386 |
| 1.1883 | 5.0 | 445 | 1.1025 | 0.7442 |
| 1.159 | 6.0 | 534 | 1.0324 | 0.7505 |
| 0.9934 | 7.0 | 623 | 0.9626 | 0.7674 |
| 0.8885 | 8.0 | 712 | 1.0080 | 0.7435 |
| 0.9325 | 9.0 | 801 | 0.9395 | 0.7681 |
| 0.9254 | 10.0 | 890 | 0.9554 | 0.7540 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
- Task
- Image Classification
- Library
- transformers
- Type
- vit
- License
- apache-2.0
- Created
- Apr 10, 2023
- Updated
- Apr 10, 2023