Downloads · 30 days
13
0% of all-time downloads
vit-base-patch16-224-int8-static-inc
INC4AI/vit-base-patch16-224-int8-static-inc
vit-base-patch16-224-int8-static-inc is a image classification model from INC4AI. 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.
This is an INT8 PyTorch model quantized with Intel® Neural Compressor.
All-time downloads
3.2K
Public
Repo size
97.8 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin97.8 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- vit
- Access
- Public
- Created
- Sep 6, 2022
- Updated
- Sep 6, 2022
- SHA
- b1f17e88
Datasets
Model card
From the Hugging Face model README
The INT8 model based on vit-base-patch16-224 which finetuned on imagenet-1k
Post-training static quantization
This is an INT8 PyTorch model quantized with Intel® Neural Compressor.
The original fp32 model comes from the fine-tuned model google/vit-base-patch16-224.
The calibration dataloader is the train dataloader. The default calibration sampling size 1000 because of 1000 classes of imagenet-1k.
The linear modules vit.encoder.layer.5.output.dense, vit.encoder.layer.9.attention.attention.query.module, fall back to fp32 for less than 1% relative accuracy loss.
Evaluation result
| INT8 | FP32 | |
|---|---|---|
| Accuracy (eval-acc) | 80.576 | 81.326 |
| Model size (MB) | 94 | 331 |
Load with Intel® Neural Compressor:
from neural_compressor.utils.load_huggingface import OptimizedModel
int8_model = OptimizedModel.from_pretrained(
'Intel/vit-base-patch16-224-int8-static',
)
- Task
- Image Classification
- Library
- transformers
- Type
- vit
- License
- apache-2.0
- Created
- Sep 6, 2022
- Updated
- Sep 6, 2022