Sponsored by ThumbnailCreator.com
Toolify Toolify logo
AI Models
nanosam

dragonSwing / nanosam

Run on huggingface.co
huggingface.co
Total runs: 0
24-hour runs: 0
7-day runs: 0
30-day runs: 0
Model's Last Updated: March 31 2024
mask-generation

Introduction of nanosam

Model Details of nanosam

NanoSAM: Accelerated Segment Anything Model for Edge deployment

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
PPHGV2-B2 200ms 12.4ms 3.2ms 29.5MB Link
PPHGV2-B4 300ms 17.3ms 4.1ms 61.4MB Link
ResNet18 500ms 22.4ms 5.8ms 63.2MB Link
EfficientViT-L0 1s 31.6ms 6ms 117.5MB -

Zero-Shot Instance Segmentation on COCO2017 validation dataset

Image Encoder mAP mask
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 
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

Runs of dragonSwing nanosam on huggingface.co

0
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs

More Information About nanosam huggingface.co Model

More nanosam license Visit here:

https://choosealicense.com/licenses/apache-2.0

nanosam huggingface.co

nanosam huggingface.co is an AI model on huggingface.co that provides nanosam's model effect (), which can be used instantly with this dragonSwing nanosam model. huggingface.co supports a free trial of the nanosam model, and also provides paid use of the nanosam. Support call nanosam model through api, including Node.js, Python, http.

nanosam huggingface.co Url

https://huggingface.co/dragonSwing/nanosam

dragonSwing nanosam online free

nanosam huggingface.co is an online trial and call api platform, which integrates nanosam's modeling effects, including api services, and provides a free online trial of nanosam, you can try nanosam online for free by clicking the link below.

dragonSwing nanosam online free url in huggingface.co:

https://huggingface.co/dragonSwing/nanosam

nanosam install

nanosam is an open source model from GitHub that offers a free installation service, and any user can find nanosam on GitHub to install. At the same time, huggingface.co provides the effect of nanosam install, users can directly use nanosam installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

nanosam install url in huggingface.co:

https://huggingface.co/dragonSwing/nanosam

Url of nanosam

Provider of nanosam huggingface.co

dragonSwing
ORGANIZATIONS
huggingface.co

Other API from dragonSwing

 huggingface.co
dragonSwing/audify

Total runs: 24
Run Growth: 1
Growth Rate: 4.17%
Updated:May 15 2022