--- library_name: pytorch license: apache-2.0 pipeline_tag: image-segmentation tags: - foundation - android --- ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam/web-assets/model_demo.png) # 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](https://github.com/facebookresearch/segment-anything). This repository provides scripts to run Segment-Anything-Model on Qualcomm® devices. More details on model performance across various devices, can be found [here](https://aihub.qualcomm.com/models/sam). ### 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 | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model |---|---|---|---|---|---|---|---|---| | SAMDecoder | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 28.971 ms | 4 - 21 MB | FP16 | NPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMDecoder.tflite) | | SAMDecoder | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 20.306 ms | 2 - 231 MB | FP16 | NPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMDecoder.tflite) | | SAMDecoder | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 16.82 ms | 3 - 163 MB | FP16 | NPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMDecoder.tflite) | | SAMDecoder | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 29.1 ms | 4 - 12 MB | FP16 | NPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMDecoder.tflite) | | SAMDecoder | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 28.998 ms | 4 - 12 MB | FP16 | NPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMDecoder.tflite) | | SAMDecoder | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 28.935 ms | 4 - 12 MB | FP16 | NPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMDecoder.tflite) | | SAMDecoder | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 29.074 ms | 4 - 12 MB | FP16 | NPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMDecoder.tflite) | | SAMDecoder | SA8295P ADP | SA8295P | TFLITE | 36.287 ms | 4 - 157 MB | FP16 | NPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMDecoder.tflite) | | SAMDecoder | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 32.956 ms | 5 - 224 MB | FP16 | NPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMDecoder.tflite) | | SAMEncoder | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 11666.822 ms | 123 - 128 MB | FP32 | CPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMEncoder.tflite) | | SAMEncoder | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 9304.036 ms | 123 - 1632 MB | FP32 | CPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMEncoder.tflite) | | SAMEncoder | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 6695.328 ms | 98 - 1575 MB | FP32 | CPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMEncoder.tflite) | | SAMEncoder | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 11003.431 ms | 123 - 127 MB | FP32 | CPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMEncoder.tflite) | | SAMEncoder | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 10520.745 ms | 123 - 127 MB | FP32 | CPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMEncoder.tflite) | | SAMEncoder | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 10821.202 ms | 123 - 127 MB | FP32 | CPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMEncoder.tflite) | | SAMEncoder | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 10167.032 ms | 41 - 132 MB | FP32 | CPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMEncoder.tflite) | | SAMEncoder | SA8295P ADP | SA8295P | TFLITE | 10764.145 ms | 124 - 1646 MB | FP32 | CPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMEncoder.tflite) | | SAMEncoder | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 13901.352 ms | 132 - 1695 MB | FP32 | CPU | [Segment-Anything-Model.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMEncoder.tflite) | ## Installation This model can be installed as a Python package via pip. ```bash 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](https://app.aihub.qualcomm.com/) 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. ```bash qai-hub configure --api_token API_TOKEN ``` Navigate to [docs](https://app.aihub.qualcomm.com/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. ```bash 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. ```bash python -m qai_hub_models.models.sam.export ``` ``` Profiling Results ------------------------------------------------------------ SAMDecoder Device : Samsung Galaxy S23 (13) Runtime : TFLITE Estimated inference time (ms) : 29.0 Estimated peak memory usage (MB): [4, 21] Total # Ops : 337 Compute Unit(s) : NPU (337 ops) ------------------------------------------------------------ SAMEncoder Device : Samsung Galaxy S23 (13) Runtime : TFLITE Estimated inference time (ms) : 11666.8 Estimated peak memory usage (MB): [123, 128] Total # Ops : 818 Compute Unit(s) : GPU (36 ops) CPU (782 ops) ``` ## How does this work? This [export script](https://aihub.qualcomm.com/models/sam/qai_hub_models/models/Segment-Anything-Model/export.py) leverages [Qualcomm® AI Hub](https://aihub.qualcomm.com/) 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. ```python import torch import qai_hub as hub from qai_hub_models.models.sam import SAMDecoder,SAMEncoder # Load the model get_sam_decoder()_model = SAMDecoder.from_pretrained() get_sam_encoder()_model = SAMEncoder.from_pretrained() # Device device = hub.Device("Samsung Galaxy S23") # Trace model get_sam_decoder()_input_shape = get_sam_decoder()_model.get_input_spec() get_sam_decoder()_sample_inputs = get_sam_decoder()_model.sample_inputs() traced_get_sam_decoder()_model = torch.jit.trace(get_sam_decoder()_model, [torch.tensor(data[0]) for _, data in get_sam_decoder()_sample_inputs.items()]) # Compile model on a specific device get_sam_decoder()_compile_job = hub.submit_compile_job( model=traced_get_sam_decoder()_model , device=device, input_specs=get_sam_decoder()_model.get_input_spec(), ) # Get target model to run on-device get_sam_decoder()_target_model = get_sam_decoder()_compile_job.get_target_model() # Trace model get_sam_encoder()_input_shape = get_sam_encoder()_model.get_input_spec() get_sam_encoder()_sample_inputs = get_sam_encoder()_model.sample_inputs() traced_get_sam_encoder()_model = torch.jit.trace(get_sam_encoder()_model, [torch.tensor(data[0]) for _, data in get_sam_encoder()_sample_inputs.items()]) # Compile model on a specific device get_sam_encoder()_compile_job = hub.submit_compile_job( model=traced_get_sam_encoder()_model , device=device, input_specs=get_sam_encoder()_model.get_input_spec(), ) # Get target model to run on-device get_sam_encoder()_target_model = get_sam_encoder()_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. ```python get_sam_decoder()_profile_job = hub.submit_profile_job( model=get_sam_decoder()_target_model, device=device, ) get_sam_encoder()_profile_job = hub.submit_profile_job( model=get_sam_encoder()_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. ```python get_sam_decoder()_input_data = get_sam_decoder()_model.sample_inputs() get_sam_decoder()_inference_job = hub.submit_inference_job( model=get_sam_decoder()_target_model, device=device, inputs=get_sam_decoder()_input_data, ) get_sam_decoder()_inference_job.download_output_data() get_sam_encoder()_input_data = get_sam_encoder()_model.sample_inputs() get_sam_encoder()_inference_job = hub.submit_inference_job( model=get_sam_encoder()_target_model, device=device, inputs=get_sam_encoder()_input_data, ) get_sam_encoder()_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](https://myaccount.qualcomm.com/signup). ## Run demo on a cloud-hosted device You can also run the demo on-device. ```bash 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 (`.tflite` export): [This tutorial](https://www.tensorflow.org/lite/android/quickstart) provides a guide to deploy the .tflite model in an Android application. - QNN (`.so` export ): This [sample app](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-50/sample_app.html) provides instructions on how to use the `.so` shared library in an Android application. ## View on Qualcomm® AI Hub Get more details on Segment-Anything-Model's performance across various devices [here](https://aihub.qualcomm.com/models/sam). Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/) ## License * The license for the original implementation of Segment-Anything-Model can be found [here](https://github.com/facebookresearch/segment-anything/blob/main/LICENSE). * The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf) ## References * [Segment Anything](https://arxiv.org/abs/2304.02643) * [Source Model Implementation](https://github.com/facebookresearch/segment-anything) ## Community * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI. * For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).