---
license: mit
library_name: timm
pipeline_tag: image-classification
tags:
- image-classification
- vision-transformer
- adaptive-inference
- elastic-inference
- imagenet-1k
- arxiv:2507.10800
datasets:
- imagenet-1k
metrics:
- accuracy
---

# ThinkingViT DeiT 3H -> 6H 800 Epochs ImageNet-1K

This repository contains the ImageNet-1K EMA weights for **ThinkingViT DeiT 3H -> 6H 800 Epochs ImageNet-1K** from
[ThinkingViT: Matryoshka Thinking Vision Transformer for Elastic Inference](https://arxiv.org/abs/2507.10800).

- Paper: https://arxiv.org/abs/2507.10800
- Hugging Face paper: https://huggingface.co/papers/2507.10800
- Code: https://github.com/ds-kiel/ThinkingViT
- Project page: https://ds-kiel.github.io/ThinkingViT-project-page/
- Exported checkpoint key: `state_dict_ema`
- Weight format: `model.safetensors`

## Usage

```python
import torch
from timm.models import create_model

# Run from the ThinkingViT repository root, or put this repository on PYTHONPATH.
model = create_model("hf-hub:NCPS/thinkingvit_deit-3h-6h-800epochs-imagenet1k", pretrained=True)
model.eval()

x = torch.randn(1, 3, 224, 224)
with torch.no_grad():
    logits, stage = model(x, threshold=1.0)
print(logits.shape, stage)
```


This is a custom timm-based architecture. Use the code from the ThinkingViT repository when loading this model.

## Threshold Behavior

The entropy threshold controls early exit. Lower thresholds send more samples to the 6-head stage; higher thresholds exit earlier at the 3-head stage.

## ImageNet-1K Results

| Threshold | Acc@1 (%) | GMACs |
|---:|---:|---:|
| 0.0 | 81.850 | 5.850 |
| 0.1 | 81.848 | 5.385 |
| 0.2 | 81.846 | 4.751 |
| 0.3 | 81.832 | 4.363 |
| 0.5 | 81.758 | 3.841 |
| 0.8 | 81.386 | 3.189 |
| 1.0 | 80.636 | 2.781 |
| 1.2 | 79.764 | 2.433 |
| 1.4 | 78.846 | 2.136 |
| 1.6 | 77.688 | 1.865 |
| 2.0 | 75.500 | 1.417 |
| 5.0 | 74.514 | 1.250 |
| 10.0 | 74.514 | 1.250 |

## Citation

Please cite the ThinkingViT paper if you use this model: https://arxiv.org/abs/2507.10800