Hugging Face's logo

qualcomm
/
Segment-Anything-Model-3

Image Segmentation
PyTorch
foundation
android
Model card Files
xet
 Community
1
qaihm-bot commited on
Commit
6b2cd80
·
verified ·
1 Parent(s): ad2bf05

v0.64.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.64.0 for changelog.

Files changed (1) hide show
  1. README.md +39 -41
README.md CHANGED
@@ -15,18 +15,18 @@ pipeline_tag: image-segmentation
15
  SAM3 (Segment Anything with Concepts) extends SAM2 with open-vocabulary segmentation, producing bounding boxes and masks for objects matching a natural-language prompt.
16
 
17
  This is based on the implementation of Segment-Anything-Model-3 found [here](https://github.com/facebookresearch/sam3).
18
- This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/sam3) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
19
 
20
  Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
21
 
22
  ## Getting Started
23
  Due to licensing restrictions, we cannot distribute pre-exported model assets for this model.
24
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/sam3) Python library to compile and export the model with your own:
25
  - Custom weights (e.g., fine-tuned checkpoints)
26
  - Custom input shapes
27
  - Target device and runtime configurations
28
 
29
- See our repository for [Segment-Anything-Model-3 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/sam3) for usage instructions.
30
 
31
 
32
  ## Model Details
@@ -44,48 +44,46 @@ See our repository for [Segment-Anything-Model-3 on GitHub](https://github.com/q
44
  ## Performance Summary
45
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
46
  |---|---|---|---|---|---|---
47
- | head | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 229.812 ms | 130 - 142 MB | NPU
48
- | head | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 272.419 ms | 131 - 142 MB | NPU
49
- | head | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | 208.75 ms | 136 - 136 MB | NPU
50
- | head | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | 471.969 ms | 663 - 663 MB | NPU
51
- | head | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 359.659 ms | 156 - 166 MB | NPU
52
- | head | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 472.887 ms | 106 - 217 MB | NPU
53
- | head | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 485.223 ms | 106 - 216 MB | NPU
54
- | head | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 471.969 ms | 663 - 663 MB | NPU
55
- | head | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 272.419 ms | 131 - 142 MB | NPU
56
- | head | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 224.248 ms | 36 - 44 MB | NPU
57
- | head | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite For Galaxy Mobile | 267.463 ms | 86 - 94 MB | NPU
58
- | head | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | 209.59 ms | 107 - 107 MB | NPU
59
- | head | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | 471.958 ms | 107 - 107 MB | NPU
60
- | head | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | 355.987 ms | 105 - 112 MB | NPU
61
- | head | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-8275 | 472.849 ms | 106 - 279 MB | NPU
62
  | head | QNN_CONTEXT_BINARY | float | Qualcomm® SA8650P | 516.497 ms | 97 - 107 MB | NPU
63
  | head | QNN_CONTEXT_BINARY | float | Qualcomm® SA8255P | 516.497 ms | 97 - 107 MB | NPU
64
- | head | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-9075 | 485.687 ms | 106 - 278 MB | NPU
65
- | head | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-X7181 | 471.958 ms | 107 - 107 MB | NPU
66
- | head | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ Q-8750 | 267.463 ms | 86 - 94 MB | NPU
67
- | head | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | 582.42 ms | 81 - 86 MB | NPU
68
- | vision_backbone | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 1201.787 ms | 78 - 90 MB | NPU
69
- | vision_backbone | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 1293.754 ms | 8 - 20 MB | NPU
70
- | vision_backbone | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | 1005.123 ms | 265 - 265 MB | NPU
71
- | vision_backbone | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | 2108.201 ms | 951 - 951 MB | NPU
72
- | vision_backbone | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1648.033 ms | 20 - 29 MB | NPU
73
- | vision_backbone | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 2461.294 ms | 16 - 32 MB | NPU
74
- | vision_backbone | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 2413.725 ms | 12 - 27 MB | NPU
75
- | vision_backbone | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 2108.201 ms | 951 - 951 MB | NPU
76
- | vision_backbone | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 1293.754 ms | 8 - 20 MB | NPU
77
- | vision_backbone | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 1090.968 ms | 6 - 19 MB | NPU
78
- | vision_backbone | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite For Galaxy Mobile | 1290.506 ms | 0 - 8 MB | NPU
79
- | vision_backbone | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | 1007.88 ms | 12 - 12 MB | NPU
80
- | vision_backbone | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | 2150.561 ms | 12 - 12 MB | NPU
81
- | vision_backbone | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | 1616.635 ms | 12 - 24 MB | NPU
82
- | vision_backbone | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-8275 | 2459.818 ms | 12 - 133 MB | NPU
83
  | vision_backbone | QNN_CONTEXT_BINARY | float | Qualcomm® SA8650P | 2520.912 ms | 1 - 11 MB | NPU
84
  | vision_backbone | QNN_CONTEXT_BINARY | float | Qualcomm® SA8255P | 2520.912 ms | 1 - 11 MB | NPU
85
- | vision_backbone | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing��� IQ-9075 | 2413.703 ms | 12 - 132 MB | NPU
86
- | vision_backbone | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-X7181 | 2150.561 ms | 12 - 12 MB | NPU
87
- | vision_backbone | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ Q-8750 | 1290.506 ms | 0 - 8 MB | NPU
88
- | vision_backbone | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | 2799.92 ms | 1 - 11 MB | NPU
89
 
90
  ## License
91
  * The license for the original implementation of Segment-Anything-Model-3 can be found
 
15
  SAM3 (Segment Anything with Concepts) extends SAM2 with open-vocabulary segmentation, producing bounding boxes and masks for objects matching a natural-language prompt.
16
 
17
  This is based on the implementation of Segment-Anything-Model-3 found [here](https://github.com/facebookresearch/sam3).
18
+ This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.64.0/src/qai_hub_models/models/sam3) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
19
 
20
  Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
21
 
22
  ## Getting Started
23
  Due to licensing restrictions, we cannot distribute pre-exported model assets for this model.
24
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.64.0/src/qai_hub_models/models/sam3) Python library to compile and export the model with your own:
25
  - Custom weights (e.g., fine-tuned checkpoints)
26
  - Custom input shapes
27
  - Target device and runtime configurations
28
 
29
+ See our repository for [Segment-Anything-Model-3 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.64.0/src/qai_hub_models/models/sam3) for usage instructions.
30
 
31
 
32
  ## Model Details
 
44
  ## Performance Summary
45
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
46
  |---|---|---|---|---|---|---
47
+ | head | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 199.555 ms | 131 - 144 MB | NPU
48
+ | head | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 294.323 ms | 130 - 142 MB | NPU
49
+ | head | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | 192.599 ms | 136 - 136 MB | NPU
50
+ | head | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | 490.286 ms | 664 - 664 MB | NPU
51
+ | head | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 403.684 ms | 131 - 140 MB | NPU
52
+ | head | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 496.148 ms | 106 - 217 MB | NPU
53
+ | head | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 503.347 ms | 106 - 216 MB | NPU
54
+ | head | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 490.286 ms | 664 - 664 MB | NPU
55
+ | head | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 294.323 ms | 130 - 142 MB | NPU
56
+ | head | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 215.164 ms | 82 - 90 MB | NPU
57
+ | head | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite For Galaxy Mobile | 294.579 ms | 81 - 93 MB | NPU
58
+ | head | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | 191.35 ms | 107 - 107 MB | NPU
59
+ | head | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | 496.047 ms | 107 - 107 MB | NPU
60
+ | head | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | 391.799 ms | 106 - 119 MB | NPU
 
61
  | head | QNN_CONTEXT_BINARY | float | Qualcomm® SA8650P | 516.497 ms | 97 - 107 MB | NPU
62
  | head | QNN_CONTEXT_BINARY | float | Qualcomm® SA8255P | 516.497 ms | 97 - 107 MB | NPU
63
+ | head | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-9075 | 502.313 ms | 106 - 278 MB | NPU
64
+ | head | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-X7181 | 496.047 ms | 107 - 107 MB | NPU
65
+ | head | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ Q-8750 | 294.579 ms | 81 - 93 MB | NPU
66
+ | head | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | 545.962 ms | 106 - 112 MB | NPU
67
+ | vision_backbone | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 1097.891 ms | 9 - 21 MB | NPU
68
+ | vision_backbone | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 1295.951 ms | 8 - 19 MB | NPU
69
+ | vision_backbone | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | 1006.596 ms | 265 - 265 MB | NPU
70
+ | vision_backbone | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | 2117.037 ms | 951 - 951 MB | NPU
71
+ | vision_backbone | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1670.675 ms | 20 - 30 MB | NPU
72
+ | vision_backbone | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 2459.713 ms | 101 - 117 MB | NPU
73
+ | vision_backbone | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 2415.958 ms | 12 - 27 MB | NPU
74
+ | vision_backbone | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 2117.037 ms | 951 - 951 MB | NPU
75
+ | vision_backbone | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 1295.951 ms | 8 - 19 MB | NPU
76
+ | vision_backbone | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 1099.147 ms | 5 - 13 MB | NPU
77
+ | vision_backbone | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite For Galaxy Mobile | 1294.463 ms | 0 - 14 MB | NPU
78
+ | vision_backbone | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | 1011.608 ms | 12 - 12 MB | NPU
79
+ | vision_backbone | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | 2142.063 ms | 12 - 12 MB | NPU
80
+ | vision_backbone | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | 1638.502 ms | 0 - 8 MB | NPU
 
81
  | vision_backbone | QNN_CONTEXT_BINARY | float | Qualcomm® SA8650P | 2520.912 ms | 1 - 11 MB | NPU
82
  | vision_backbone | QNN_CONTEXT_BINARY | float | Qualcomm® SA8255P | 2520.912 ms | 1 - 11 MB | NPU
83
+ | vision_backbone | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-9075 | 2413.638 ms | 12 - 132 MB | NPU
84
+ | vision_backbone | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-X7181 | 2142.063 ms | 12 - 12 MB | NPU
85
+ | vision_backbone | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ Q-8750 | 1294.463 ms | 0 - 14 MB | NPU
86
+ | vision_backbone | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | 2799.918 ms | 11 - 21 MB | NPU
87
 
88
  ## License
89
  * The license for the original implementation of Segment-Anything-Model-3 can be found