|
--- |
|
license: apache-2.0 |
|
pipeline_tag: mask-generation |
|
--- |
|
|
|
# NanoSAM: Accelerated Segment Anything Model for Edge deployment |
|
|
|
- [GitHub](https://github.com/binh234/nanosam) |
|
- [Demo](https://huggingface.co/spaces/dragonSwing/nanosam) |
|
|
|
## Pretrained Models |
|
|
|
NanoSAM performance on edge devices. Latency/throughput is measured on NVIDIA Jetson Xavier NX, and NVIDIA T4 GPU with TensorRT, fp16. Data transfer time is included. |
|
|
|
| Image Encoder | CPU | Jetson Xavier NX | T4 | Model size | Download | |
|
| --------------- | :---: | :--------------: | :---: | :--------: | :------------------------------------------------------------------------------------------------------: | |
|
| PPHGV2-B1 | 110ms | 9.6ms | 2.4ms | 12.7MB | [Link](https://huggingface.co/dragonSwing/nanosam/resolve/main/sam_hgv2_b1_ln_nonorm_image_encoder.onnx) | |
|
| PPHGV2-B2 | 200ms | 12.4ms | 3.2ms | 29.5MB | [Link](https://huggingface.co/dragonSwing/nanosam/resolve/main/sam_hgv2_b1_ln_nonorm_image_encoder.onnx) | |
|
| PPHGV2-B4 | 300ms | 17.3ms | 4.1ms | 61.4MB | [Link](https://huggingface.co/dragonSwing/nanosam/resolve/main/sam_hgv2_b1_ln_nonorm_image_encoder.onnx) | |
|
| ResNet18 | 500ms | 22.4ms | 5.8ms | 63.2MB | [Link](https://drive.google.com/file/d/14-SsvoaTl-esC3JOzomHDnI9OGgdO2OR/view?usp=drive_link) | |
|
| EfficientViT-L0 | 1s | 31.6ms | 6ms | 117.5MB | - | |
|
|
|
Zero-Shot Instance Segmentation on COCO2017 validation dataset |
|
|
|
| Image Encoder | mAP<sup>mask<br>50-95 | mIoU (all) | mIoU (large) | mIoU (medium) | mIoU (small) | |
|
| --------------- | :-------------------: | :--------: | :----------: | :-----------: | :----------: | |
|
| ResNet18 | - | 70.6 | 79.6 | 73.8 | 62.4 | |
|
| MobileSAM | - | 72.8 | 80.4 | 75.9 | 65.8 | |
|
| PPHGV2-B1 | 41.2 | 75.6 | 81.2 | 77.4 | 70.8 | |
|
| PPHGV2-B2 | 42.6 | 76.5 | 82.2 | 78.5 | 71.5 | |
|
| PPHGV2-B4 | 44.0 | 77.3 | 83.0 | 79.7 | 72.1 | |
|
| EfficientViT-L0 | 45.6 | 78.6 | 83.7 | 81.0 | 73.3 | |
|
|
|
## Usage |
|
|
|
```python3 |
|
from nanosam.utils.predictor import Predictor |
|
|
|
image_encoder_cfg = { |
|
"path": "data/sam_hgv2_b4_ln_nonorm_image_encoder.onnx", |
|
"name": "OnnxModel", |
|
"provider": "cpu", |
|
"normalize_input": False, |
|
} |
|
mask_decoder_cfg = { |
|
"path": "data/efficientvit_l0_mask_decoder.onnx", |
|
"name": "OnnxModel", |
|
"provider": "cpu", |
|
} |
|
predictor = Predictor(encoder_cfg, decoder_cfg) |
|
|
|
image = PIL.Image.open("assets/dogs.jpg") |
|
|
|
predictor.set_image(image) |
|
|
|
mask, _, _ = predictor.predict(np.array([[x, y]]), np.array([1])) |
|
``` |
|
|
|
The point labels may be |
|
|
|
| Point Label | Description | |
|
| :---------: | ------------------------- | |
|
| 0 | Background point | |
|
| 1 | Foreground point | |
|
| 2 | Bounding box top-left | |
|
| 3 | Bounding box bottom-right | |
|
|
