Sponsored by
Agentkit
qualcomm / Segment-Anything-Model
Model's Last Updated: May 16 2025
image-segmentation
Introduction of Segment-Anything-Model
Model Details of Segment-Anything-Model
Segment-Anything-Model: Optimized for Mobile Deployment
High-quality segmentation mask generation around any object in an image with simple input prompt
Transformer based encoder-decoder where prompts specify what to segment in an image thereby allowing segmentation without the need for additional training. The image encoder generates embeddings and the lightweight decoder operates on the embeddings for point and mask based image segmentation.
This model is an implementation of Segment-Anything-Model found here . This repository provides scripts to run Segment-Anything-Model on Qualcomm® devices. More details on model performance across various devices, can be found here .
Model Details
- Model Type: Semantic segmentation
-
Model Stats:
- Model checkpoint: vit_l
- Input resolution: 720p (720x1280)
- Number of parameters (SAMDecoder): 5.11M
- Model size (SAMDecoder): 19.6 MB
| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model |
|---|---|---|---|---|---|---|---|
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 48.448 ms | 4 - 17 MB | FP16 | NPU | SAMDecoder.tflite |
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 12267.436 ms | 2517 - 2522 MB | FP32 | CPU | SAMEncoder.tflite |
Installation
This model can be installed as a Python package via pip.
pip install "qai-hub-models[sam]"
Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
Sign-in to
Qualcomm® AI Hub
with your
Qualcomm® ID. Once signed in navigate to
Account -> Settings -> API Token
.
With this API token, you can configure your client to run models on the cloud hosted devices.
qai-hub configure --api_token API_TOKEN
Navigate to docs for more information.
Demo off target
The package contains a simple end-to-end demo that downloads pre-trained weights and runs this model on a sample input.
python -m qai_hub_models.models.sam.demo
The above demo runs a reference implementation of pre-processing, model inference, and post processing.
NOTE : If you want running in a Jupyter Notebook or Google Colab like environment, please add the following to your cell (instead of the above).
%run -m qai_hub_models.models.sam.demo
Run model on a cloud-hosted device
In addition to the demo, you can also run the model on a cloud-hosted Qualcomm® device. This script does the following:
- Performance check on-device on a cloud-hosted device
- Downloads compiled assets that can be deployed on-device for Android.
- Accuracy check between PyTorch and on-device outputs.
python -m qai_hub_models.models.sam.export
Profile Job summary of SAMDecoder
--------------------------------------------------
Device: QCS8550 (Proxy) (12)
Estimated Inference Time: 47.86 ms
Estimated Peak Memory Range: 3.86-6.07 MB
Compute Units: NPU (341) | Total (341)
Profile Job summary of SAMEncoder
--------------------------------------------------
Device: QCS8550 (Proxy) (12)
Estimated Inference Time: 11666.28 ms
Estimated Peak Memory Range: 2526.26-2529.86 MB
Compute Units: GPU (37),CPU (783) | Total (820)
How does this work?
This export script leverages Qualcomm® AI Hub to optimize, validate, and deploy this model on-device. Lets go through each step below in detail:
Step 1: Compile model for on-device deployment
To compile a PyTorch model for on-device deployment, we first trace the model
in memory using the
jit.trace
and then call the
submit_compile_job
API.
import torch
import qai_hub as hub
from qai_hub_models.models.sam import Model
# Load the model
torch_model = Model.from_pretrained()
# Device
device = hub.Device("Samsung Galaxy S23")
# Trace model
input_shape = torch_model.get_input_spec()
sample_inputs = torch_model.sample_inputs()
pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()])
# Compile model on a specific device
compile_job = hub.submit_compile_job(
model=pt_model,
device=device,
input_specs=torch_model.get_input_spec(),
)
# Get target model to run on-device
target_model = compile_job.get_target_model()
Step 2: Performance profiling on cloud-hosted device
After compiling models from step 1. Models can be profiled model on-device using the
target_model
. Note that this scripts runs the model on a device automatically
provisioned in the cloud. Once the job is submitted, you can navigate to a
provided job URL to view a variety of on-device performance metrics.
profile_job = hub.submit_profile_job(
model=target_model,
device=device,
)
Step 3: Verify on-device accuracy
To verify the accuracy of the model on-device, you can run on-device inference on sample input data on the same cloud hosted device.
input_data = torch_model.sample_inputs()
inference_job = hub.submit_inference_job(
model=target_model,
device=device,
inputs=input_data,
)
on_device_output = inference_job.download_output_data()
With the output of the model, you can compute like PSNR, relative errors or spot check the output with expected output.
Note : This on-device profiling and inference requires access to Qualcomm® AI Hub. Sign up for access .
Run demo on a cloud-hosted device
You can also run the demo on-device.
python -m qai_hub_models.models.sam.demo --on-device
NOTE : If you want running in a Jupyter Notebook or Google Colab like environment, please add the following to your cell (instead of the above).
%run -m qai_hub_models.models.sam.demo -- --on-device
Deploying compiled model to Android
The models can be deployed using multiple runtimes:
-
TensorFlow Lite (
.tfliteexport): This tutorial provides a guide to deploy the .tflite model in an Android application. -
QNN (
.soexport ): This sample app provides instructions on how to use the.soshared library in an Android application.
View on Qualcomm® AI Hub
Get more details on Segment-Anything-Model's performance across various devices here . Explore all available models on Qualcomm® AI Hub
License
- The license for the original implementation of Segment-Anything-Model can be found here .
- The license for the compiled assets for on-device deployment can be found here
References
Community
- Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
- For questions or feedback please reach out to us .
Runs of qualcomm Segment-Anything-Model on huggingface.co
2.5K
Total runs
15
24-hour runs
90
3-day runs
768
7-day runs
1.7K
30-day runs
More Information About Segment-Anything-Model huggingface.co Model
Url of Segment-Anything-Model
Segment-Anything-Model huggingface.co Url
Provider of Segment-Anything-Model huggingface.co
Other API from qualcomm
Total runs:
2.4K
Run Growth:
1.2K
Growth Rate:
65.55%
Total runs:
1.9K
Run Growth:
1.2K
Growth Rate:
84.98%
Total runs:
1.9K
Run Growth:
525
Growth Rate:
28.15%
Total runs:
1.7K
Run Growth:
698
Growth Rate:
41.65%
Total runs:
1.4K
Run Growth:
324
Growth Rate:
29.08%
Total runs:
1.2K
Run Growth:
389
Growth Rate:
37.26%
Total runs:
1.1K
Run Growth:
466
Growth Rate:
44.13%
Total runs:
1.0K
Run Growth:
816
Growth Rate:
78.16%
Total runs:
593
Run Growth:
129
Growth Rate:
21.75%
Total runs:
584
Run Growth:
380
Growth Rate:
65.07%
Total runs:
563
Run Growth:
0
Growth Rate:
0.00%
Total runs:
507
Run Growth:
264
Growth Rate:
70.59%
Total runs:
472
Run Growth:
78
Growth Rate:
16.53%
Total runs:
468
Run Growth:
0
Growth Rate:
0.00%
Total runs:
444
Run Growth:
0
Growth Rate:
0.00%
Total runs:
418
Run Growth:
0
Growth Rate:
0.00%
Total runs:
412
Run Growth:
-13
Growth Rate:
-3.16%
Total runs:
411
Run Growth:
0
Growth Rate:
0.00%
Total runs:
396
Run Growth:
0
Growth Rate:
0.00%
Total runs:
371
Run Growth:
-5
Growth Rate:
-1.35%
Total runs:
336
Run Growth:
0
Growth Rate:
0.00%
Total runs:
316
Run Growth:
-600
Growth Rate:
-189.87%
Total runs:
278
Run Growth:
-643
Growth Rate:
-231.29%
Total runs:
261
Run Growth:
-78
Growth Rate:
-29.89%
Total runs:
260
Run Growth:
169
Growth Rate:
67.33%
Total runs:
245
Run Growth:
30
Growth Rate:
12.24%
Total runs:
234
Run Growth:
27
Growth Rate:
11.54%
Total runs:
205
Run Growth:
0
Growth Rate:
0.00%
Total runs:
204
Run Growth:
95
Growth Rate:
45.89%
Total runs:
202
Run Growth:
40
Growth Rate:
19.80%
Total runs:
183
Run Growth:
-63
Growth Rate:
-34.43%
Total runs:
180
Run Growth:
122
Growth Rate:
67.78%
Total runs:
172
Run Growth:
-20
Growth Rate:
-11.63%
Total runs:
172
Run Growth:
-20
Growth Rate:
-11.63%
Total runs:
163
Run Growth:
-397
Growth Rate:
-243.56%
Total runs:
153
Run Growth:
0
Growth Rate:
0.00%
Total runs:
136
Run Growth:
-83
Growth Rate:
-61.03%
Total runs:
115
Run Growth:
78
Growth Rate:
67.83%
Total runs:
109
Run Growth:
0
Growth Rate:
0.00%
Total runs:
107
Run Growth:
-46
Growth Rate:
-42.99%
Total runs:
105
Run Growth:
0
Growth Rate:
0.00%
Total runs:
97
Run Growth:
0
Growth Rate:
0.00%
Total runs:
93
Run Growth:
0
Growth Rate:
0.00%
Total runs:
87
Run Growth:
0
Growth Rate:
0.00%
Total runs:
82
Run Growth:
-54
Growth Rate:
-65.85%
Total runs:
81
Run Growth:
4
Growth Rate:
4.94%
Total runs:
72
Run Growth:
0
Growth Rate:
0.00%
Total runs:
70
Run Growth:
31
Growth Rate:
44.29%