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 7.496 ms 0 - 29 MB FP16 NPU Segment-Anything-Model.tflite
SAMDecoder Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 7.297 ms 4 - 26 MB FP16 NPU Segment-Anything-Model.so
SAMDecoder Samsung Galaxy S23 Snapdragon® 8 Gen 2 ONNX 10.997 ms 1 - 59 MB FP16 NPU Segment-Anything-Model.onnx
SAMDecoder Samsung Galaxy S24 Snapdragon® 8 Gen 3 TFLITE 5.194 ms 0 - 39 MB FP16 NPU Segment-Anything-Model.tflite
SAMDecoder Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 5.138 ms 4 - 45 MB FP16 NPU Segment-Anything-Model.so
SAMDecoder Samsung Galaxy S24 Snapdragon® 8 Gen 3 ONNX 7.908 ms 4 - 58 MB FP16 NPU Segment-Anything-Model.onnx
SAMDecoder Snapdragon 8 Elite QRD Snapdragon® 8 Elite TFLITE 5.022 ms 0 - 35 MB FP16 NPU Segment-Anything-Model.tflite
SAMDecoder Snapdragon 8 Elite QRD Snapdragon® 8 Elite QNN 4.808 ms 4 - 43 MB FP16 NPU Use Export Script
SAMDecoder Snapdragon 8 Elite QRD Snapdragon® 8 Elite ONNX 8.33 ms 3 - 48 MB FP16 NPU Segment-Anything-Model.onnx
SAMDecoder QCS8550 (Proxy) QCS8550 Proxy TFLITE 7.482 ms 0 - 34 MB FP16 NPU Segment-Anything-Model.tflite
SAMDecoder QCS8550 (Proxy) QCS8550 Proxy QNN 6.833 ms 4 - 7 MB FP16 NPU Use Export Script
SAMDecoder SA7255P ADP SA7255P TFLITE 53.072 ms 0 - 31 MB FP16 NPU Segment-Anything-Model.tflite
SAMDecoder SA7255P ADP SA7255P QNN 49.854 ms 2 - 9 MB FP16 NPU Use Export Script
SAMDecoder SA8255 (Proxy) SA8255P Proxy TFLITE 7.488 ms 0 - 33 MB FP16 NPU Segment-Anything-Model.tflite
SAMDecoder SA8255 (Proxy) SA8255P Proxy QNN 6.856 ms 4 - 6 MB FP16 NPU Use Export Script
SAMDecoder SA8295P ADP SA8295P TFLITE 10.448 ms 0 - 35 MB FP16 NPU Segment-Anything-Model.tflite
SAMDecoder SA8295P ADP SA8295P QNN 9.023 ms 0 - 14 MB FP16 NPU Use Export Script
SAMDecoder SA8650 (Proxy) SA8650P Proxy TFLITE 7.468 ms 0 - 31 MB FP16 NPU Segment-Anything-Model.tflite
SAMDecoder SA8650 (Proxy) SA8650P Proxy QNN 6.898 ms 4 - 7 MB FP16 NPU Use Export Script
SAMDecoder SA8775P ADP SA8775P TFLITE 10.481 ms 0 - 32 MB FP16 NPU Segment-Anything-Model.tflite
SAMDecoder SA8775P ADP SA8775P QNN 9.672 ms 1 - 11 MB FP16 NPU Use Export Script
SAMDecoder QCS8450 (Proxy) QCS8450 Proxy TFLITE 8.944 ms 0 - 39 MB FP16 NPU Segment-Anything-Model.tflite
SAMDecoder QCS8450 (Proxy) QCS8450 Proxy QNN 8.3 ms 4 - 47 MB FP16 NPU Use Export Script
SAMDecoder Snapdragon X Elite CRD Snapdragon® X Elite QNN 7.387 ms 4 - 4 MB FP16 NPU Use Export Script
SAMDecoder Snapdragon X Elite CRD Snapdragon® X Elite ONNX 14.654 ms 13 - 13 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart1 Samsung Galaxy S23 Snapdragon® 8 Gen 2 TFLITE 209.019 ms 12 - 69 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart1 Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 205.936 ms 12 - 93 MB FP16 NPU Segment-Anything-Model.so
SAMEncoderPart1 Samsung Galaxy S23 Snapdragon® 8 Gen 2 ONNX 170.285 ms 25 - 176 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart1 Samsung Galaxy S24 Snapdragon® 8 Gen 3 TFLITE 148.733 ms 10 - 653 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart1 Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 146.052 ms 12 - 652 MB FP16 NPU Segment-Anything-Model.so
SAMEncoderPart1 Samsung Galaxy S24 Snapdragon® 8 Gen 3 ONNX 120.931 ms 24 - 696 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart1 Snapdragon 8 Elite QRD Snapdragon® 8 Elite TFLITE 146.901 ms 12 - 670 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart1 Snapdragon 8 Elite QRD Snapdragon® 8 Elite QNN 142.17 ms 3 - 654 MB FP16 NPU Use Export Script
SAMEncoderPart1 Snapdragon 8 Elite QRD Snapdragon® 8 Elite ONNX 108.126 ms 24 - 673 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart1 QCS8550 (Proxy) QCS8550 Proxy TFLITE 209.39 ms 12 - 78 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart1 QCS8550 (Proxy) QCS8550 Proxy QNN 175.952 ms 12 - 15 MB FP16 NPU Use Export Script
SAMEncoderPart1 SA7255P ADP SA7255P TFLITE 1176.456 ms 12 - 655 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart1 SA7255P ADP SA7255P QNN 1101.014 ms 4 - 12 MB FP16 NPU Use Export Script
SAMEncoderPart1 SA8255 (Proxy) SA8255P Proxy TFLITE 208.032 ms 12 - 74 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart1 SA8255 (Proxy) SA8255P Proxy QNN 178.079 ms 12 - 15 MB FP16 NPU Use Export Script
SAMEncoderPart1 SA8295P ADP SA8295P TFLITE 243.729 ms 12 - 640 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart1 SA8295P ADP SA8295P QNN 207.581 ms 0 - 14 MB FP16 NPU Use Export Script
SAMEncoderPart1 SA8650 (Proxy) SA8650P Proxy TFLITE 206.899 ms 12 - 79 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart1 SA8650 (Proxy) SA8650P Proxy QNN 178.981 ms 12 - 14 MB FP16 NPU Use Export Script
SAMEncoderPart1 SA8775P ADP SA8775P TFLITE 252.41 ms 12 - 655 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart1 SA8775P ADP SA8775P QNN 211.388 ms 1 - 11 MB FP16 NPU Use Export Script
SAMEncoderPart1 QCS8450 (Proxy) QCS8450 Proxy TFLITE 232.157 ms 12 - 995 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart1 QCS8450 (Proxy) QCS8450 Proxy QNN 222.335 ms 4 - 965 MB FP16 NPU Use Export Script
SAMEncoderPart1 Snapdragon X Elite CRD Snapdragon® X Elite QNN 171.549 ms 12 - 12 MB FP16 NPU Use Export Script
SAMEncoderPart1 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 181.095 ms 38 - 38 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart2 Samsung Galaxy S23 Snapdragon® 8 Gen 2 TFLITE 654.976 ms 12 - 110 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart2 Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 832.207 ms 12 - 110 MB FP16 NPU Segment-Anything-Model.so
SAMEncoderPart2 Samsung Galaxy S23 Snapdragon® 8 Gen 2 ONNX 694.809 ms 0 - 201 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart2 Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 661.317 ms 12 - 1110 MB FP16 NPU Segment-Anything-Model.so
SAMEncoderPart2 Snapdragon 8 Elite QRD Snapdragon® 8 Elite TFLITE 472.889 ms 12 - 1148 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart2 Snapdragon 8 Elite QRD Snapdragon® 8 Elite QNN 528.224 ms 12 - 1115 MB FP16 NPU Use Export Script
SAMEncoderPart2 Snapdragon 8 Elite QRD Snapdragon® 8 Elite ONNX 462.973 ms 25 - 1409 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart2 QCS8550 (Proxy) QCS8550 Proxy TFLITE 654.376 ms 12 - 104 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart2 QCS8550 (Proxy) QCS8550 Proxy QNN 728.462 ms 12 - 14 MB FP16 NPU Use Export Script
SAMEncoderPart2 SA8255 (Proxy) SA8255P Proxy TFLITE 684.138 ms 12 - 104 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart2 SA8255 (Proxy) SA8255P Proxy QNN 744.998 ms 12 - 15 MB FP16 NPU Use Export Script
SAMEncoderPart2 SA8295P ADP SA8295P TFLITE 704.249 ms 12 - 1176 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart2 SA8295P ADP SA8295P QNN 782.37 ms 0 - 14 MB FP16 NPU Use Export Script
SAMEncoderPart2 SA8650 (Proxy) SA8650P Proxy TFLITE 624.867 ms 12 - 110 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart2 SA8650 (Proxy) SA8650P Proxy QNN 743.875 ms 12 - 14 MB FP16 NPU Use Export Script
SAMEncoderPart2 SA8775P ADP SA8775P TFLITE 722.805 ms 0 - 1144 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart2 SA8775P ADP SA8775P QNN 739.926 ms 1 - 11 MB FP16 NPU Use Export Script
SAMEncoderPart2 Snapdragon X Elite CRD Snapdragon® X Elite QNN 635.324 ms 12 - 12 MB FP16 NPU Use Export Script
SAMEncoderPart2 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 741.229 ms 52 - 52 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart3 Samsung Galaxy S23 Snapdragon® 8 Gen 2 TFLITE 659.742 ms 12 - 114 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart3 Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 849.715 ms 1 - 107 MB FP16 NPU Segment-Anything-Model.so
SAMEncoderPart3 Samsung Galaxy S23 Snapdragon® 8 Gen 2 ONNX 687.45 ms 12 - 211 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart3 Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 682.052 ms 12 - 1108 MB FP16 NPU Segment-Anything-Model.so
SAMEncoderPart3 Samsung Galaxy S24 Snapdragon® 8 Gen 3 ONNX 609.933 ms 24 - 1425 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart3 Snapdragon 8 Elite QRD Snapdragon® 8 Elite TFLITE 423.957 ms 12 - 1149 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart3 Snapdragon 8 Elite QRD Snapdragon® 8 Elite QNN 577.926 ms 12 - 1114 MB FP16 NPU Use Export Script
SAMEncoderPart3 Snapdragon 8 Elite QRD Snapdragon® 8 Elite ONNX 463.85 ms 24 - 1409 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart3 QCS8550 (Proxy) QCS8550 Proxy TFLITE 658.397 ms 12 - 105 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart3 QCS8550 (Proxy) QCS8550 Proxy QNN 719.036 ms 12 - 14 MB FP16 NPU Use Export Script
SAMEncoderPart3 SA7255P ADP SA7255P QNN 1877.658 ms 4 - 13 MB FP16 NPU Use Export Script
SAMEncoderPart3 SA8255 (Proxy) SA8255P Proxy TFLITE 658.984 ms 12 - 106 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart3 SA8255 (Proxy) SA8255P Proxy QNN 746.128 ms 12 - 15 MB FP16 NPU Use Export Script
SAMEncoderPart3 SA8295P ADP SA8295P TFLITE 707.389 ms 11 - 1169 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart3 SA8295P ADP SA8295P QNN 780.808 ms 0 - 15 MB FP16 NPU Use Export Script
SAMEncoderPart3 SA8650 (Proxy) SA8650P Proxy TFLITE 650.209 ms 12 - 104 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart3 SA8650 (Proxy) SA8650P Proxy QNN 741.658 ms 12 - 14 MB FP16 NPU Use Export Script
SAMEncoderPart3 SA8775P ADP SA8775P TFLITE 699.588 ms 0 - 1145 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart3 Snapdragon X Elite CRD Snapdragon® X Elite QNN 682.704 ms 12 - 12 MB FP16 NPU Use Export Script
SAMEncoderPart3 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 741.666 ms 53 - 53 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart4 Samsung Galaxy S23 Snapdragon® 8 Gen 2 TFLITE 660.425 ms 12 - 103 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart4 Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 850.796 ms 12 - 111 MB FP16 NPU Segment-Anything-Model.so
SAMEncoderPart4 Samsung Galaxy S23 Snapdragon® 8 Gen 2 ONNX 735.756 ms 24 - 217 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart4 Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 676.625 ms 3 - 1105 MB FP16 NPU Segment-Anything-Model.so
SAMEncoderPart4 Samsung Galaxy S24 Snapdragon® 8 Gen 3 ONNX 606.957 ms 23 - 1418 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart4 Snapdragon 8 Elite QRD Snapdragon® 8 Elite TFLITE 469.821 ms 11 - 1144 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart4 Snapdragon 8 Elite QRD Snapdragon® 8 Elite QNN 574.694 ms 10 - 1118 MB FP16 NPU Use Export Script
SAMEncoderPart4 Snapdragon 8 Elite QRD Snapdragon® 8 Elite ONNX 462.452 ms 36 - 1417 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart4 QCS8550 (Proxy) QCS8550 Proxy TFLITE 661.229 ms 12 - 103 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart4 QCS8550 (Proxy) QCS8550 Proxy QNN 727.569 ms 12 - 15 MB FP16 NPU Use Export Script
SAMEncoderPart4 SA7255P ADP SA7255P QNN 1869.043 ms 8 - 17 MB FP16 NPU Use Export Script
SAMEncoderPart4 SA8255 (Proxy) SA8255P Proxy TFLITE 662.568 ms 12 - 103 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart4 SA8255 (Proxy) SA8255P Proxy QNN 733.293 ms 12 - 14 MB FP16 NPU Use Export Script
SAMEncoderPart4 SA8295P ADP SA8295P TFLITE 706.266 ms 12 - 1172 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart4 SA8295P ADP SA8295P QNN 784.772 ms 0 - 15 MB FP16 NPU Use Export Script
SAMEncoderPart4 SA8650 (Proxy) SA8650P Proxy TFLITE 656.939 ms 12 - 108 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart4 SA8650 (Proxy) SA8650P Proxy QNN 741.153 ms 12 - 14 MB FP16 NPU Use Export Script
SAMEncoderPart4 SA8775P ADP SA8775P TFLITE 717.416 ms 0 - 1143 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart4 SA8775P ADP SA8775P QNN 739.764 ms 6 - 15 MB FP16 NPU Use Export Script
SAMEncoderPart4 Snapdragon X Elite CRD Snapdragon® X Elite QNN 629.135 ms 12 - 12 MB FP16 NPU Use Export Script
SAMEncoderPart4 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 742.285 ms 52 - 52 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart5 Samsung Galaxy S23 Snapdragon® 8 Gen 2 TFLITE 664.891 ms 12 - 102 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart5 Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 818.349 ms 12 - 120 MB FP16 NPU Segment-Anything-Model.so
SAMEncoderPart5 Samsung Galaxy S23 Snapdragon® 8 Gen 2 ONNX 752.745 ms 24 - 211 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart5 Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 666.563 ms 6 - 1101 MB FP16 NPU Segment-Anything-Model.so
SAMEncoderPart5 Samsung Galaxy S24 Snapdragon® 8 Gen 3 ONNX 578.332 ms 18 - 1423 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart5 Snapdragon 8 Elite QRD Snapdragon® 8 Elite TFLITE 471.325 ms 12 - 1147 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart5 Snapdragon 8 Elite QRD Snapdragon® 8 Elite QNN 577.197 ms 12 - 1114 MB FP16 NPU Use Export Script
SAMEncoderPart5 Snapdragon 8 Elite QRD Snapdragon® 8 Elite ONNX 461.817 ms 36 - 1424 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart5 QCS8550 (Proxy) QCS8550 Proxy TFLITE 655.75 ms 12 - 118 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart5 QCS8550 (Proxy) QCS8550 Proxy QNN 749.162 ms 12 - 15 MB FP16 NPU Use Export Script
SAMEncoderPart5 SA7255P ADP SA7255P QNN 1874.378 ms 4 - 13 MB FP16 NPU Use Export Script
SAMEncoderPart5 SA8255 (Proxy) SA8255P Proxy TFLITE 665.3 ms 12 - 113 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart5 SA8255 (Proxy) SA8255P Proxy QNN 736.349 ms 12 - 14 MB FP16 NPU Use Export Script
SAMEncoderPart5 SA8295P ADP SA8295P TFLITE 1.844674407370935e+16 ms 12 - 1172 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart5 SA8295P ADP SA8295P QNN 783.84 ms 1 - 15 MB FP16 NPU Use Export Script
SAMEncoderPart5 SA8650 (Proxy) SA8650P Proxy TFLITE 654.117 ms 12 - 115 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart5 SA8650 (Proxy) SA8650P Proxy QNN 743.603 ms 12 - 15 MB FP16 NPU Use Export Script
SAMEncoderPart5 SA8775P ADP SA8775P TFLITE 718.325 ms 0 - 1144 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart5 SA8775P ADP SA8775P QNN 740.649 ms 12 - 22 MB FP16 NPU Use Export Script
SAMEncoderPart5 Snapdragon X Elite CRD Snapdragon® X Elite QNN 633.494 ms 12 - 12 MB FP16 NPU Use Export Script
SAMEncoderPart5 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 742.408 ms 52 - 52 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart6 Samsung Galaxy S23 Snapdragon® 8 Gen 2 TFLITE 655.189 ms 12 - 108 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart6 Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 807.274 ms 12 - 120 MB FP16 NPU Segment-Anything-Model.so
SAMEncoderPart6 Samsung Galaxy S23 Snapdragon® 8 Gen 2 ONNX 755.205 ms 12 - 204 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart6 Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 668.409 ms 1212 - 2314 MB FP16 NPU Segment-Anything-Model.so
SAMEncoderPart6 Samsung Galaxy S24 Snapdragon® 8 Gen 3 ONNX 584.922 ms 24 - 1421 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart6 Snapdragon 8 Elite QRD Snapdragon® 8 Elite TFLITE 475.467 ms 11 - 1140 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart6 Snapdragon 8 Elite QRD Snapdragon® 8 Elite QNN 528.924 ms 10 - 1114 MB FP16 NPU Use Export Script
SAMEncoderPart6 Snapdragon 8 Elite QRD Snapdragon® 8 Elite ONNX 439.119 ms 36 - 1413 MB FP16 NPU Segment-Anything-Model.onnx
SAMEncoderPart6 QCS8550 (Proxy) QCS8550 Proxy TFLITE 665.633 ms 12 - 108 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart6 QCS8550 (Proxy) QCS8550 Proxy QNN 727.32 ms 12 - 15 MB FP16 NPU Use Export Script
SAMEncoderPart6 SA8255 (Proxy) SA8255P Proxy TFLITE 667.805 ms 12 - 107 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart6 SA8255 (Proxy) SA8255P Proxy QNN 742.425 ms 12 - 14 MB FP16 NPU Use Export Script
SAMEncoderPart6 SA8295P ADP SA8295P TFLITE 706.978 ms 12 - 1175 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart6 SA8295P ADP SA8295P QNN 784.131 ms 0 - 14 MB FP16 NPU Use Export Script
SAMEncoderPart6 SA8650 (Proxy) SA8650P Proxy TFLITE 675.893 ms 12 - 115 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart6 SA8650 (Proxy) SA8650P Proxy QNN 739.078 ms 12 - 15 MB FP16 NPU Use Export Script
SAMEncoderPart6 SA8775P ADP SA8775P TFLITE 703.126 ms 0 - 1144 MB FP16 NPU Segment-Anything-Model.tflite
SAMEncoderPart6 SA8775P ADP SA8775P QNN 740.372 ms 1 - 11 MB FP16 NPU Use Export Script
SAMEncoderPart6 Snapdragon X Elite CRD Snapdragon® X Elite QNN 634.143 ms 12 - 12 MB FP16 NPU Use Export Script
SAMEncoderPart6 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 726.741 ms 51 - 51 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)   : 7.5                    
Estimated peak memory usage (MB): [0, 29]                
Total # Ops                     : 845                    
Compute Unit(s)                 : NPU (845 ops)          

------------------------------------------------------------
SAMEncoderPart1
Device                          : Samsung Galaxy S23 (13)
Runtime                         : TFLITE                 
Estimated inference time (ms)   : 209.0                  
Estimated peak memory usage (MB): [12, 69]               
Total # Ops                     : 585                    
Compute Unit(s)                 : NPU (585 ops)          

------------------------------------------------------------
SAMEncoderPart2
Device                          : Samsung Galaxy S23 (13)
Runtime                         : TFLITE                 
Estimated inference time (ms)   : 655.0                  
Estimated peak memory usage (MB): [12, 110]              
Total # Ops                     : 573                    
Compute Unit(s)                 : NPU (573 ops)          

------------------------------------------------------------
SAMEncoderPart3
Device                          : Samsung Galaxy S23 (13)
Runtime                         : TFLITE                 
Estimated inference time (ms)   : 659.7                  
Estimated peak memory usage (MB): [12, 114]              
Total # Ops                     : 573                    
Compute Unit(s)                 : NPU (573 ops)          

------------------------------------------------------------
SAMEncoderPart4
Device                          : Samsung Galaxy S23 (13)
Runtime                         : TFLITE                 
Estimated inference time (ms)   : 660.4                  
Estimated peak memory usage (MB): [12, 103]              
Total # Ops                     : 573                    
Compute Unit(s)                 : NPU (573 ops)          

------------------------------------------------------------
SAMEncoderPart5
Device                          : Samsung Galaxy S23 (13)
Runtime                         : TFLITE                 
Estimated inference time (ms)   : 664.9                  
Estimated peak memory usage (MB): [12, 102]              
Total # Ops                     : 573                    
Compute Unit(s)                 : NPU (573 ops)          

------------------------------------------------------------
SAMEncoderPart6
Device                          : Samsung Galaxy S23 (13)
Runtime                         : TFLITE                 
Estimated inference time (ms)   : 655.2                  
Estimated peak memory usage (MB): [12, 108]              
Total # Ops                     : 573                    
Compute Unit(s)                 : NPU (573 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.