---
license: apache-2.0
pipeline_tag: mask-generation
---

# EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss

- [Paper](https://arxiv.org/abs/2402.05008)
- [GitHub](https://github.com/mit-han-lab/efficientvit)
- [Demo](https://evitsam.hanlab.ai/)

## Pretrained Models

Latency/Throughput is measured on NVIDIA Jetson AGX Orin, and NVIDIA A100 GPU with TensorRT, fp16. Data transfer time is included.

| Model         |  Resolution | COCO mAP | LVIS mAP | Params |  MACs | Jetson Orin Latency (bs1) | A100 Throughput (bs16) | Checkpoint |
|----------------------|:----------:|:----------:|:---------:|:------------:|:---------:|:---------:|:------------:|:------------:|
| EfficientViT-SAM-L0 | 512x512 | 45.7 | 41.8 | 34.8M  | 35G | 8.2ms  | 762 images/s | [link](https://huggingface.co/mit-han-lab/efficientvit-sam/resolve/main/efficientvit_sam_l0.pt?download=true) |
| EfficientViT-SAM-L1 | 512x512 | 46.2 | 42.1 | 47.7M | 49G |  10.2ms | 638 images/s | [link](https://huggingface.co/mit-han-lab/efficientvit-sam/resolve/main/efficientvit_sam_l1.pt?download=true) |
| EfficientViT-SAM-L2 | 512x512 | 46.6 | 42.7 | 61.3M | 69G |  12.9ms | 538 images/s  | [link](https://huggingface.co/mit-han-lab/efficientvit-sam/resolve/main/efficientvit_sam_l2.pt?download=true) |
| EfficientViT-SAM-XL0 | 1024x1024 | 47.5 | 43.9 | 117.0M | 185G | 22.5ms  | 278 images/s | [link](https://huggingface.co/mit-han-lab/efficientvit-sam/resolve/main/efficientvit_sam_xl0.pt?download=true) |
| EfficientViT-SAM-XL1 | 1024x1024 | 47.8 | 44.4 | 203.3M | 322G | 37.2ms  | 182 images/s | [link](https://huggingface.co/mit-han-lab/efficientvit-sam/resolve/main/efficientvit_sam_xl1.pt?download=true) |
<p align="center">
<b> Table1: Summary of All EfficientViT-SAM Variants.</b> COCO mAP and LVIS mAP are measured using ViTDet's predicted bounding boxes as the prompt. End-to-end Jetson Orin latency and A100 throughput are measured with TensorRT and fp16.
</p>

## Usage

```python
# segment anything
from efficientvit.sam_model_zoo import create_sam_model

efficientvit_sam = create_sam_model(
  name="xl1", weight_url="assets/checkpoints/sam/xl1.pt",
)
efficientvit_sam = efficientvit_sam.cuda().eval()
```

```python
from efficientvit.models.efficientvit.sam import EfficientViTSamPredictor

efficientvit_sam_predictor = EfficientViTSamPredictor(efficientvit_sam)
```

```python
from efficientvit.models.efficientvit.sam import EfficientViTSamAutomaticMaskGenerator

efficientvit_mask_generator = EfficientViTSamAutomaticMaskGenerator(efficientvit_sam)

```