Hugging Face's logo

qualcomm
/
Segment-Anything-Model

Image Segmentation
PyTorch
TF Lite
ONNX
foundation
android
Model card Files Community

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
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 7.557 ms 0 - 31 MB FP16 NPU Segment-Anything-Model.tflite
SAMDecoder Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 7.052 ms 4 - 19 MB FP16 NPU Segment-Anything-Model.so
SAMDecoder Samsung Galaxy S23 Snapdragon® 8 Gen 2 ONNX 11.415 ms 0 - 266 MB FP16 NPU Segment-Anything-Model.onnx
SAMDecoder Samsung Galaxy S24 Snapdragon® 8 Gen 3 TFLITE 5.23 ms 0 - 39 MB FP16 NPU Segment-Anything-Model.tflite
SAMDecoder Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 4.973 ms 4 - 46 MB FP16 NPU Segment-Anything-Model.so
SAMDecoder Samsung Galaxy S24 Snapdragon® 8 Gen 3 ONNX 7.741 ms 5 - 126 MB FP16 NPU Segment-Anything-Model.onnx
SAMDecoder Snapdragon 8 Elite QRD Snapdragon® 8 Elite TFLITE 5.18 ms 0 - 35 MB FP16 NPU Segment-Anything-Model.tflite
SAMDecoder Snapdragon 8 Elite QRD Snapdragon® 8 Elite QNN 3.787 ms 4 - 42 MB FP16 NPU Use Export Script
SAMDecoder Snapdragon 8 Elite QRD Snapdragon® 8 Elite ONNX 8.231 ms 0 - 86 MB FP16 NPU Segment-Anything-Model.onnx
SAMDecoder QCS8550 (Proxy) QCS8550 Proxy TFLITE 7.484 ms 0 - 33 MB FP16 NPU Segment-Anything-Model.tflite
SAMDecoder QCS8550 (Proxy) QCS8550 Proxy QNN 6.814 ms 4 - 5 MB FP16 NPU Use Export Script
SAMDecoder SA7255P ADP SA7255P TFLITE 52.929 ms 0 - 32 MB FP16 NPU Segment-Anything-Model.tflite
SAMDecoder SA7255P ADP SA7255P QNN 50.031 ms 2 - 11 MB FP16 NPU Use Export Script
SAMDecoder SA8255 (Proxy) SA8255P Proxy TFLITE 7.484 ms 0 - 32 MB FP16 NPU Segment-Anything-Model.tflite
SAMDecoder SA8255 (Proxy) SA8255P Proxy QNN 6.852 ms 4 - 5 MB FP16 NPU Use Export Script
SAMDecoder SA8295P ADP SA8295P TFLITE 9.976 ms 0 - 35 MB FP16 NPU Segment-Anything-Model.tflite
SAMDecoder SA8295P ADP SA8295P QNN 9.05 ms 0 - 6 MB FP16 NPU Use Export Script
SAMDecoder SA8650 (Proxy) SA8650P Proxy TFLITE 7.477 ms 0 - 29 MB FP16 NPU Segment-Anything-Model.tflite
SAMDecoder SA8650 (Proxy) SA8650P Proxy QNN 6.893 ms 4 - 6 MB FP16 NPU Use Export Script
SAMDecoder SA8775P ADP SA8775P TFLITE 10.51 ms 0 - 34 MB FP16 NPU Segment-Anything-Model.tflite
SAMDecoder SA8775P ADP SA8775P QNN 9.667 ms 0 - 6 MB FP16 NPU Use Export Script
SAMDecoder QCS8450 (Proxy) QCS8450 Proxy TFLITE 8.533 ms 0 - 37 MB FP16 NPU Segment-Anything-Model.tflite
SAMDecoder QCS8450 (Proxy) QCS8450 Proxy QNN 8.315 ms 4 - 44 MB FP16 NPU Use Export Script
SAMDecoder Snapdragon X Elite CRD Snapdragon® X Elite QNN 7.458 ms 4 - 4 MB FP16 NPU Use Export Script
SAMDecoder Snapdragon X Elite CRD Snapdragon® X Elite ONNX 14.75 ms 12 - 12 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart1 Samsung Galaxy S23 Snapdragon® 8 Gen 2 TFLITE 208.201 ms 12 - 74 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart1 Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 203.885 ms 12 - 67 MB FP16 NPU Segment-Anything-Model.so
SAMEncoderPart1 Samsung Galaxy S23 Snapdragon® 8 Gen 2 ONNX 168.865 ms 12 - 57 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart1 Samsung Galaxy S24 Snapdragon® 8 Gen 3 TFLITE 149.759 ms 11 - 660 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart1 Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 144.476 ms 364 - 1006 MB FP16 NPU Segment-Anything-Model.so
SAMEncoderPart1 Samsung Galaxy S24 Snapdragon® 8 Gen 3 ONNX 121.68 ms 0 - 1234 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart1 Snapdragon 8 Elite QRD Snapdragon® 8 Elite TFLITE 128.622 ms 11 - 667 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart1 Snapdragon 8 Elite QRD Snapdragon® 8 Elite QNN 141.432 ms 3 - 655 MB FP16 NPU Use Export Script
SAMEncoderPart1 Snapdragon 8 Elite QRD Snapdragon® 8 Elite ONNX 96.596 ms 39 - 1086 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart1 QCS8550 (Proxy) QCS8550 Proxy TFLITE 205.315 ms 12 - 81 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart1 QCS8550 (Proxy) QCS8550 Proxy QNN 177.157 ms 12 - 14 MB FP16 NPU Use Export Script
SAMEncoderPart1 SA7255P ADP SA7255P TFLITE 1173.558 ms 2 - 646 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart1 SA7255P ADP SA7255P QNN 1100.71 ms 4 - 13 MB FP16 NPU Use Export Script
SAMEncoderPart1 SA8255 (Proxy) SA8255P Proxy TFLITE 208.837 ms 12 - 70 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart1 SA8255 (Proxy) SA8255P Proxy QNN 178.44 ms 12 - 14 MB FP16 NPU Use Export Script
SAMEncoderPart1 SA8295P ADP SA8295P TFLITE 242.752 ms 12 - 640 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart1 SA8295P ADP SA8295P QNN 206.972 ms 0 - 6 MB FP16 NPU Use Export Script
SAMEncoderPart1 SA8650 (Proxy) SA8650P Proxy TFLITE 208.397 ms 12 - 65 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart1 SA8650 (Proxy) SA8650P Proxy QNN 177.673 ms 13 - 14 MB FP16 NPU Use Export Script
SAMEncoderPart1 SA8775P ADP SA8775P TFLITE 251.286 ms 12 - 656 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart1 SA8775P ADP SA8775P QNN 211.825 ms 3 - 9 MB FP16 NPU Use Export Script
SAMEncoderPart1 QCS8450 (Proxy) QCS8450 Proxy TFLITE 226.498 ms 12 - 995 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart1 QCS8450 (Proxy) QCS8450 Proxy QNN 219.929 ms 9 - 964 MB FP16 NPU Use Export Script
SAMEncoderPart1 Snapdragon X Elite CRD Snapdragon® X Elite QNN 171.827 ms 12 - 12 MB FP16 NPU Use Export Script
SAMEncoderPart1 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 179.691 ms 39 - 39 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart2 Samsung Galaxy S23 Snapdragon® 8 Gen 2 TFLITE 670.133 ms 12 - 104 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart2 Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 838.379 ms 12 - 109 MB FP16 NPU Segment-Anything-Model.so
SAMEncoderPart2 Samsung Galaxy S23 Snapdragon® 8 Gen 2 ONNX 722.337 ms 0 - 54 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart2 Samsung Galaxy S24 Snapdragon® 8 Gen 3 TFLITE 556.374 ms 11 - 1092 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart2 Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 668.897 ms 12 - 1113 MB FP16 NPU Segment-Anything-Model.so
SAMEncoderPart2 Snapdragon 8 Elite QRD Snapdragon® 8 Elite TFLITE 487.43 ms 12 - 1100 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart2 Snapdragon 8 Elite QRD Snapdragon® 8 Elite QNN 574.723 ms 10 - 1113 MB FP16 NPU Use Export Script
SAMEncoderPart2 Snapdragon 8 Elite QRD Snapdragon® 8 Elite ONNX 474.562 ms 41 - 4748 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart2 QCS8550 (Proxy) QCS8550 Proxy TFLITE 671.625 ms 0 - 102 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart2 QCS8550 (Proxy) QCS8550 Proxy QNN 737.788 ms 13 - 14 MB FP16 NPU Use Export Script
SAMEncoderPart2 SA7255P ADP SA7255P QNN 1869.513 ms 0 - 10 MB FP16 NPU Use Export Script
SAMEncoderPart2 SA8255 (Proxy) SA8255P Proxy TFLITE 690.907 ms 12 - 116 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart2 SA8255 (Proxy) SA8255P Proxy QNN 731.994 ms 15 - 16 MB FP16 NPU Use Export Script
SAMEncoderPart2 SA8295P ADP SA8295P TFLITE 726.454 ms 12 - 1141 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart2 SA8295P ADP SA8295P QNN 782.399 ms 0 - 6 MB FP16 NPU Use Export Script
SAMEncoderPart2 SA8650 (Proxy) SA8650P Proxy TFLITE 671.719 ms 12 - 104 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart2 SA8650 (Proxy) SA8650P Proxy QNN 733.997 ms 12 - 14 MB FP16 NPU Use Export Script
SAMEncoderPart2 SA8775P ADP SA8775P TFLITE 717.157 ms 0 - 1105 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart2 Snapdragon X Elite CRD Snapdragon® X Elite QNN 633.76 ms 12 - 12 MB FP16 NPU Use Export Script
SAMEncoderPart2 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 743.453 ms 51 - 51 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart3 Samsung Galaxy S23 Snapdragon® 8 Gen 2 TFLITE 686.379 ms 12 - 103 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart3 Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 852.964 ms 12 - 115 MB FP16 NPU Segment-Anything-Model.so
SAMEncoderPart3 Samsung Galaxy S23 Snapdragon® 8 Gen 2 ONNX 740.438 ms 9 - 62 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart3 Snapdragon 8 Elite QRD Snapdragon® 8 Elite TFLITE 440.773 ms 12 - 1099 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart3 Snapdragon 8 Elite QRD Snapdragon® 8 Elite QNN 579.622 ms 11 - 1115 MB FP16 NPU Use Export Script
SAMEncoderPart3 Snapdragon 8 Elite QRD Snapdragon® 8 Elite ONNX 472.649 ms 39 - 4748 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart3 QCS8550 (Proxy) QCS8550 Proxy TFLITE 668.273 ms 12 - 114 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart3 QCS8550 (Proxy) QCS8550 Proxy QNN 731.938 ms 12 - 14 MB FP16 NPU Use Export Script
SAMEncoderPart3 SA7255P ADP SA7255P QNN 1874.534 ms 12 - 22 MB FP16 NPU Use Export Script
SAMEncoderPart3 SA8255 (Proxy) SA8255P Proxy TFLITE 684.379 ms 12 - 108 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart3 SA8255 (Proxy) SA8255P Proxy QNN 731.638 ms 13 - 15 MB FP16 NPU Use Export Script
SAMEncoderPart3 SA8295P ADP SA8295P TFLITE 725.387 ms 12 - 1148 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart3 SA8295P ADP SA8295P QNN 781.146 ms 0 - 6 MB FP16 NPU Use Export Script
SAMEncoderPart3 SA8650 (Proxy) SA8650P Proxy TFLITE 683.645 ms 12 - 112 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart3 SA8650 (Proxy) SA8650P Proxy QNN 735.421 ms 13 - 14 MB FP16 NPU Use Export Script
SAMEncoderPart3 SA8775P ADP SA8775P TFLITE 724.877 ms 0 - 1107 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart3 SA8775P ADP SA8775P QNN 742.231 ms 1 - 11 MB FP16 NPU Use Export Script
SAMEncoderPart3 Snapdragon X Elite CRD Snapdragon® X Elite QNN 632.458 ms 12 - 12 MB FP16 NPU Use Export Script
SAMEncoderPart3 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 741.655 ms 51 - 51 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart4 Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 833.428 ms 12 - 100 MB FP16 NPU Segment-Anything-Model.so
SAMEncoderPart4 Samsung Galaxy S23 Snapdragon® 8 Gen 2 ONNX 682.163 ms 0 - 53 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart4 Snapdragon 8 Elite QRD Snapdragon® 8 Elite TFLITE 437.593 ms 11 - 1098 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart4 Snapdragon 8 Elite QRD Snapdragon® 8 Elite QNN 531.361 ms 10 - 1119 MB FP16 NPU Use Export Script
SAMEncoderPart4 Snapdragon 8 Elite QRD Snapdragon® 8 Elite ONNX 563.94 ms 26 - 5204 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart4 QCS8550 (Proxy) QCS8550 Proxy TFLITE 675.986 ms 12 - 102 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart4 QCS8550 (Proxy) QCS8550 Proxy QNN 731.308 ms 12 - 14 MB FP16 NPU Use Export Script
SAMEncoderPart4 SA8255 (Proxy) SA8255P Proxy TFLITE 677.387 ms 12 - 103 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart4 SA8255 (Proxy) SA8255P Proxy QNN 740.258 ms 13 - 14 MB FP16 NPU Use Export Script
SAMEncoderPart4 SA8295P ADP SA8295P TFLITE 725.343 ms 12 - 1150 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart4 SA8295P ADP SA8295P QNN 782.501 ms 0 - 6 MB FP16 NPU Use Export Script
SAMEncoderPart4 SA8650 (Proxy) SA8650P Proxy TFLITE 674.544 ms 12 - 102 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart4 SA8650 (Proxy) SA8650P Proxy QNN 745.54 ms 13 - 14 MB FP16 NPU Use Export Script
SAMEncoderPart4 SA8775P ADP SA8775P QNN 738.7 ms 12 - 22 MB FP16 NPU Use Export Script
SAMEncoderPart4 Snapdragon X Elite CRD Snapdragon® X Elite QNN 628.108 ms 12 - 12 MB FP16 NPU Use Export Script
SAMEncoderPart4 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 739.45 ms 53 - 53 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart5 Samsung Galaxy S23 Snapdragon® 8 Gen 2 TFLITE 671.428 ms 12 - 107 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart5 Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 844.265 ms 12 - 102 MB FP16 NPU Segment-Anything-Model.so
SAMEncoderPart5 Samsung Galaxy S23 Snapdragon® 8 Gen 2 ONNX 684.639 ms 0 - 53 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart5 Samsung Galaxy S24 Snapdragon® 8 Gen 3 TFLITE 548.457 ms 12 - 1096 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart5 Snapdragon 8 Elite QRD Snapdragon® 8 Elite TFLITE 484.471 ms 11 - 1099 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart5 Snapdragon 8 Elite QRD Snapdragon® 8 Elite QNN 575.509 ms 7 - 1111 MB FP16 NPU Use Export Script
SAMEncoderPart5 Snapdragon 8 Elite QRD Snapdragon® 8 Elite ONNX 470.838 ms 39 - 4742 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart5 QCS8550 (Proxy) QCS8550 Proxy TFLITE 665.458 ms 12 - 104 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart5 QCS8550 (Proxy) QCS8550 Proxy QNN 720.635 ms 12 - 14 MB FP16 NPU Use Export Script
SAMEncoderPart5 SA7255P ADP SA7255P QNN 1874.681 ms 11 - 22 MB FP16 NPU Use Export Script
SAMEncoderPart5 SA8255 (Proxy) SA8255P Proxy TFLITE 691.758 ms 12 - 113 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart5 SA8255 (Proxy) SA8255P Proxy QNN 745.957 ms 13 - 14 MB FP16 NPU Use Export Script
SAMEncoderPart5 SA8295P ADP SA8295P TFLITE 725.701 ms 12 - 1149 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart5 SA8295P ADP SA8295P QNN 782.525 ms 0 - 6 MB FP16 NPU Use Export Script
SAMEncoderPart5 SA8650 (Proxy) SA8650P Proxy TFLITE 679.545 ms 12 - 105 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart5 SA8650 (Proxy) SA8650P Proxy QNN 730.129 ms 13 - 15 MB FP16 NPU Use Export Script
SAMEncoderPart5 SA8775P ADP SA8775P QNN 741.02 ms 1 - 11 MB FP16 NPU Use Export Script
SAMEncoderPart5 Snapdragon X Elite CRD Snapdragon® X Elite QNN 640.949 ms 12 - 12 MB FP16 NPU Use Export Script
SAMEncoderPart5 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 735.548 ms 51 - 51 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart6 Samsung Galaxy S23 Snapdragon® 8 Gen 2 TFLITE 677.701 ms 12 - 102 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart6 Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 841.659 ms 12 - 109 MB FP16 NPU Segment-Anything-Model.so
SAMEncoderPart6 Samsung Galaxy S23 Snapdragon® 8 Gen 2 ONNX 684.635 ms 0 - 935 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart6 Samsung Galaxy S24 Snapdragon® 8 Gen 3 TFLITE 536.637 ms 10 - 1099 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart6 Snapdragon 8 Elite QRD Snapdragon® 8 Elite TFLITE 485.849 ms 11 - 1093 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart6 Snapdragon 8 Elite QRD Snapdragon® 8 Elite QNN 579.641 ms 10 - 1114 MB FP16 NPU Use Export Script
SAMEncoderPart6 Snapdragon 8 Elite QRD Snapdragon® 8 Elite ONNX 472.01 ms 39 - 4745 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart6 QCS8550 (Proxy) QCS8550 Proxy TFLITE 656.062 ms 12 - 113 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart6 QCS8550 (Proxy) QCS8550 Proxy QNN 730.888 ms 12 - 14 MB FP16 NPU Use Export Script
SAMEncoderPart6 SA7255P ADP SA7255P QNN 1868.576 ms 5 - 15 MB FP16 NPU Use Export Script
SAMEncoderPart6 SA8255 (Proxy) SA8255P Proxy TFLITE 688.443 ms 12 - 102 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart6 SA8255 (Proxy) SA8255P Proxy QNN 736.226 ms 12 - 14 MB FP16 NPU Use Export Script
SAMEncoderPart6 SA8295P ADP SA8295P TFLITE 725.807 ms 5 - 1142 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart6 SA8295P ADP SA8295P QNN 782.131 ms 0 - 6 MB FP16 NPU Use Export Script
SAMEncoderPart6 SA8650 (Proxy) SA8650P Proxy TFLITE 672.876 ms 12 - 104 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart6 SA8650 (Proxy) SA8650P Proxy QNN 740.495 ms 16 - 18 MB FP16 NPU Use Export Script
SAMEncoderPart6 SA8775P ADP SA8775P TFLITE 726.536 ms 0 - 1104 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart6 SA8775P ADP SA8775P QNN 742.038 ms 2 - 12 MB FP16 NPU Use Export Script
SAMEncoderPart6 Snapdragon X Elite CRD Snapdragon® X Elite QNN 629.137 ms 12 - 12 MB FP16 NPU Use Export Script
SAMEncoderPart6 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 743.947 ms 52 - 52 MB FP16 NPU Segment-Anything-Model.onnx

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

Profiling Results
------------------------------------------------------------
SAMDecoder
Device                          : Samsung Galaxy S23 (13)
Runtime                         : TFLITE                 
Estimated inference time (ms)   : 7.6                    
Estimated peak memory usage (MB): [0, 31]                
Total # Ops                     : 845                    
Compute Unit(s)                 : NPU (845 ops)          

------------------------------------------------------------
SAMEncoderPart1
Device                          : Samsung Galaxy S23 (13)
Runtime                         : TFLITE                 
Estimated inference time (ms)   : 208.2                  
Estimated peak memory usage (MB): [12, 74]               
Total # Ops                     : 585                    
Compute Unit(s)                 : NPU (585 ops)          

------------------------------------------------------------
SAMEncoderPart2
Device                          : Samsung Galaxy S23 (13)
Runtime                         : TFLITE                 
Estimated inference time (ms)   : 670.1                  
Estimated peak memory usage (MB): [12, 104]              
Total # Ops                     : 580                    
Compute Unit(s)                 : NPU (580 ops)          

------------------------------------------------------------
SAMEncoderPart3
Device                          : Samsung Galaxy S23 (13)
Runtime                         : TFLITE                 
Estimated inference time (ms)   : 686.4                  
Estimated peak memory usage (MB): [12, 103]              
Total # Ops                     : 580                    
Compute Unit(s)                 : NPU (580 ops)          

------------------------------------------------------------
SAMEncoderPart4
Device                          : Samsung Galaxy S23 (13)
Runtime                         : QNN                    
Estimated inference time (ms)   : 833.4                  
Estimated peak memory usage (MB): [12, 100]              
Total # Ops                     : 613                    
Compute Unit(s)                 : NPU (613 ops)          

------------------------------------------------------------
SAMEncoderPart5
Device                          : Samsung Galaxy S23 (13)
Runtime                         : TFLITE                 
Estimated inference time (ms)   : 671.4                  
Estimated peak memory usage (MB): [12, 107]              
Total # Ops                     : 580                    
Compute Unit(s)                 : NPU (580 ops)          

------------------------------------------------------------
SAMEncoderPart6
Device                          : Samsung Galaxy S23 (13)
Runtime                         : TFLITE                 
Estimated inference time (ms)   : 677.7                  
Estimated peak memory usage (MB): [12, 102]              
Total # Ops                     : 580                    
Compute Unit(s)                 : NPU (580 ops)

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
model = Model.from_pretrained()
decoder_model = model.decoder
encoder_splits[0]_model = model.encoder_splits[0]
encoder_splits[1]_model = model.encoder_splits[1]
encoder_splits[2]_model = model.encoder_splits[2]
encoder_splits[3]_model = model.encoder_splits[3]
encoder_splits[4]_model = model.encoder_splits[4]
encoder_splits[5]_model = model.encoder_splits[5]

# Device
device = hub.Device("Samsung Galaxy S23")

# Trace model
decoder_input_shape = decoder_model.get_input_spec()
decoder_sample_inputs = decoder_model.sample_inputs()

traced_decoder_model = torch.jit.trace(decoder_model, [torch.tensor(data[0]) for _, data in decoder_sample_inputs.items()])

# Compile model on a specific device
decoder_compile_job = hub.submit_compile_job(
    model=traced_decoder_model ,
    device=device,
    input_specs=decoder_model.get_input_spec(),
)

# Get target model to run on-device
decoder_target_model = decoder_compile_job.get_target_model()
# Trace model
encoder_splits[0]_input_shape = encoder_splits[0]_model.get_input_spec()
encoder_splits[0]_sample_inputs = encoder_splits[0]_model.sample_inputs()

traced_encoder_splits[0]_model = torch.jit.trace(encoder_splits[0]_model, [torch.tensor(data[0]) for _, data in encoder_splits[0]_sample_inputs.items()])

# Compile model on a specific device
encoder_splits[0]_compile_job = hub.submit_compile_job(
    model=traced_encoder_splits[0]_model ,
    device=device,
    input_specs=encoder_splits[0]_model.get_input_spec(),
)

# Get target model to run on-device
encoder_splits[0]_target_model = encoder_splits[0]_compile_job.get_target_model()
# Trace model
encoder_splits[1]_input_shape = encoder_splits[1]_model.get_input_spec()
encoder_splits[1]_sample_inputs = encoder_splits[1]_model.sample_inputs()

traced_encoder_splits[1]_model = torch.jit.trace(encoder_splits[1]_model, [torch.tensor(data[0]) for _, data in encoder_splits[1]_sample_inputs.items()])

# Compile model on a specific device
encoder_splits[1]_compile_job = hub.submit_compile_job(
    model=traced_encoder_splits[1]_model ,
    device=device,
    input_specs=encoder_splits[1]_model.get_input_spec(),
)

# Get target model to run on-device
encoder_splits[1]_target_model = encoder_splits[1]_compile_job.get_target_model()
# Trace model
encoder_splits[2]_input_shape = encoder_splits[2]_model.get_input_spec()
encoder_splits[2]_sample_inputs = encoder_splits[2]_model.sample_inputs()

traced_encoder_splits[2]_model = torch.jit.trace(encoder_splits[2]_model, [torch.tensor(data[0]) for _, data in encoder_splits[2]_sample_inputs.items()])

# Compile model on a specific device
encoder_splits[2]_compile_job = hub.submit_compile_job(
    model=traced_encoder_splits[2]_model ,
    device=device,
    input_specs=encoder_splits[2]_model.get_input_spec(),
)

# Get target model to run on-device
encoder_splits[2]_target_model = encoder_splits[2]_compile_job.get_target_model()
# Trace model
encoder_splits[3]_input_shape = encoder_splits[3]_model.get_input_spec()
encoder_splits[3]_sample_inputs = encoder_splits[3]_model.sample_inputs()

traced_encoder_splits[3]_model = torch.jit.trace(encoder_splits[3]_model, [torch.tensor(data[0]) for _, data in encoder_splits[3]_sample_inputs.items()])

# Compile model on a specific device
encoder_splits[3]_compile_job = hub.submit_compile_job(
    model=traced_encoder_splits[3]_model ,
    device=device,
    input_specs=encoder_splits[3]_model.get_input_spec(),
)

# Get target model to run on-device
encoder_splits[3]_target_model = encoder_splits[3]_compile_job.get_target_model()
# Trace model
encoder_splits[4]_input_shape = encoder_splits[4]_model.get_input_spec()
encoder_splits[4]_sample_inputs = encoder_splits[4]_model.sample_inputs()

traced_encoder_splits[4]_model = torch.jit.trace(encoder_splits[4]_model, [torch.tensor(data[0]) for _, data in encoder_splits[4]_sample_inputs.items()])

# Compile model on a specific device
encoder_splits[4]_compile_job = hub.submit_compile_job(
    model=traced_encoder_splits[4]_model ,
    device=device,
    input_specs=encoder_splits[4]_model.get_input_spec(),
)

# Get target model to run on-device
encoder_splits[4]_target_model = encoder_splits[4]_compile_job.get_target_model()
# Trace model
encoder_splits[5]_input_shape = encoder_splits[5]_model.get_input_spec()
encoder_splits[5]_sample_inputs = encoder_splits[5]_model.sample_inputs()

traced_encoder_splits[5]_model = torch.jit.trace(encoder_splits[5]_model, [torch.tensor(data[0]) for _, data in encoder_splits[5]_sample_inputs.items()])

# Compile model on a specific device
encoder_splits[5]_compile_job = hub.submit_compile_job(
    model=traced_encoder_splits[5]_model ,
    device=device,
    input_specs=encoder_splits[5]_model.get_input_spec(),
)

# Get target model to run on-device
encoder_splits[5]_target_model = encoder_splits[5]_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.

decoder_profile_job = hub.submit_profile_job(
    model=decoder_target_model,
    device=device,
)
encoder_splits[0]_profile_job = hub.submit_profile_job(
    model=encoder_splits[0]_target_model,
    device=device,
)
encoder_splits[1]_profile_job = hub.submit_profile_job(
    model=encoder_splits[1]_target_model,
    device=device,
)
encoder_splits[2]_profile_job = hub.submit_profile_job(
    model=encoder_splits[2]_target_model,
    device=device,
)
encoder_splits[3]_profile_job = hub.submit_profile_job(
    model=encoder_splits[3]_target_model,
    device=device,
)
encoder_splits[4]_profile_job = hub.submit_profile_job(
    model=encoder_splits[4]_target_model,
    device=device,
)
encoder_splits[5]_profile_job = hub.submit_profile_job(
    model=encoder_splits[5]_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.

decoder_input_data = decoder_model.sample_inputs()
decoder_inference_job = hub.submit_inference_job(
    model=decoder_target_model,
    device=device,
    inputs=decoder_input_data,
)
decoder_inference_job.download_output_data()
encoder_splits[0]_input_data = encoder_splits[0]_model.sample_inputs()
encoder_splits[0]_inference_job = hub.submit_inference_job(
    model=encoder_splits[0]_target_model,
    device=device,
    inputs=encoder_splits[0]_input_data,
)
encoder_splits[0]_inference_job.download_output_data()
encoder_splits[1]_input_data = encoder_splits[1]_model.sample_inputs()
encoder_splits[1]_inference_job = hub.submit_inference_job(
    model=encoder_splits[1]_target_model,
    device=device,
    inputs=encoder_splits[1]_input_data,
)
encoder_splits[1]_inference_job.download_output_data()
encoder_splits[2]_input_data = encoder_splits[2]_model.sample_inputs()
encoder_splits[2]_inference_job = hub.submit_inference_job(
    model=encoder_splits[2]_target_model,
    device=device,
    inputs=encoder_splits[2]_input_data,
)
encoder_splits[2]_inference_job.download_output_data()
encoder_splits[3]_input_data = encoder_splits[3]_model.sample_inputs()
encoder_splits[3]_inference_job = hub.submit_inference_job(
    model=encoder_splits[3]_target_model,
    device=device,
    inputs=encoder_splits[3]_input_data,
)
encoder_splits[3]_inference_job.download_output_data()
encoder_splits[4]_input_data = encoder_splits[4]_model.sample_inputs()
encoder_splits[4]_inference_job = hub.submit_inference_job(
    model=encoder_splits[4]_target_model,
    device=device,
    inputs=encoder_splits[4]_input_data,
)
encoder_splits[4]_inference_job.download_output_data()
encoder_splits[5]_input_data = encoder_splits[5]_model.sample_inputs()
encoder_splits[5]_inference_job = hub.submit_inference_job(
    model=encoder_splits[5]_target_model,
    device=device,
    inputs=encoder_splits[5]_input_data,
)
encoder_splits[5]_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 (.tflite export): This tutorial provides a guide to deploy the .tflite model in an Android application.

  • QNN (.so export ): This sample app 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. 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

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Examples
Image Segmentation
Inference API (serverless) does not yet support pytorch models for this pipeline type.