Hugging Face's logo

qualcomm
/
MaskRCNN

Image Segmentation
PyTorch
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
e4af9ad
·
verified ·
1 Parent(s): 7302e3f

v0.53.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.53.0 for changelog.

Files changed (2) hide show
  1. README.md +29 -25
  2. release_assets.json +2 -2
README.md CHANGED
@@ -27,7 +27,7 @@ Below are pre-exported model assets ready for deployment.
27
 
28
  | Runtime | Precision | Chipset | SDK Versions | Download |
29
  |---|---|---|---|---|
30
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/maskrcnn/releases/v0.52.0/maskrcnn-qnn_dlc-float.zip)
31
 
32
  For more device-specific assets and performance metrics, visit **[MaskRCNN on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/maskrcnn)**.
33
 
@@ -57,30 +57,34 @@ See our repository for [MaskRCNN on GitHub](https://github.com/qualcomm/ai-hub-m
57
  ## Performance Summary
58
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
59
  |---|---|---|---|---|---|---
60
- | proposal_generator | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 43.422 ms | 5 - 1768 MB | NPU
61
- | proposal_generator | QNN_DLC | float | Snapdragon® X2 Elite | 42.858 ms | 7 - 7 MB | NPU
62
- | proposal_generator | QNN_DLC | float | Snapdragon® X Elite | 91.314 ms | 7 - 7 MB | NPU
63
- | proposal_generator | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 69.805 ms | 7 - 2326 MB | NPU
64
- | proposal_generator | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 353.675 ms | 0 - 1756 MB | NPU
65
- | proposal_generator | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 95.28 ms | 7 - 10 MB | NPU
66
- | proposal_generator | QNN_DLC | float | Qualcomm® SA8775P | 122.387 ms | 1 - 1757 MB | NPU
67
- | proposal_generator | QNN_DLC | float | Qualcomm® QCS9075 | 119.13 ms | 7 - 71 MB | NPU
68
- | proposal_generator | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 157.312 ms | 7 - 2737 MB | NPU
69
- | proposal_generator | QNN_DLC | float | Qualcomm® SA7255P | 353.675 ms | 0 - 1756 MB | NPU
70
- | proposal_generator | QNN_DLC | float | Qualcomm® SA8295P | 125.92 ms | 0 - 1430 MB | NPU
71
- | proposal_generator | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 53.369 ms | 0 - 1509 MB | NPU
72
- | roi_head | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 94.707 ms | 51 - 750 MB | NPU
73
- | roi_head | QNN_DLC | float | Snapdragon® X2 Elite | 100.686 ms | 52 - 52 MB | NPU
74
- | roi_head | QNN_DLC | float | Snapdragon® X Elite | 236.847 ms | 52 - 52 MB | NPU
75
- | roi_head | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 180.955 ms | 42 - 891 MB | NPU
76
- | roi_head | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 572.679 ms | 39 - 735 MB | NPU
77
- | roi_head | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 250.521 ms | 52 - 55 MB | NPU
78
- | roi_head | QNN_DLC | float | Qualcomm® SA8775P | 267.972 ms | 49 - 923 MB | NPU
79
- | roi_head | QNN_DLC | float | Qualcomm® QCS9075 | 321.626 ms | 52 - 106 MB | NPU
80
- | roi_head | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 297.834 ms | 39 - 955 MB | NPU
81
- | roi_head | QNN_DLC | float | Qualcomm® SA7255P | 572.679 ms | 39 - 735 MB | NPU
82
- | roi_head | QNN_DLC | float | Qualcomm® SA8295P | 307.15 ms | 49 - 846 MB | NPU
83
- | roi_head | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 123.331 ms | 23 - 714 MB | NPU
 
 
 
 
84
 
85
  ## License
86
  * The license for the original implementation of MaskRCNN can be found
 
27
 
28
  | Runtime | Precision | Chipset | SDK Versions | Download |
29
  |---|---|---|---|---|
30
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/maskrcnn/releases/v0.53.0/maskrcnn-qnn_dlc-float.zip)
31
 
32
  For more device-specific assets and performance metrics, visit **[MaskRCNN on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/maskrcnn)**.
33
 
 
57
  ## Performance Summary
58
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
59
  |---|---|---|---|---|---|---
60
+ | proposal_generator | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 44.202 ms | 7 - 1769 MB | NPU
61
+ | proposal_generator | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 53.244 ms | 0 - 1510 MB | NPU
62
+ | proposal_generator | QNN_DLC | float | Snapdragon® X2 Elite | 43.187 ms | 7 - 7 MB | NPU
63
+ | proposal_generator | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 69.276 ms | 7 - 2329 MB | NPU
64
+ | proposal_generator | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 353.892 ms | 0 - 1756 MB | NPU
65
+ | proposal_generator | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 95.916 ms | 7 - 24 MB | NPU
66
+ | proposal_generator | QNN_DLC | float | Qualcomm® SA8775P | 122.39 ms | 0 - 1756 MB | NPU
67
+ | proposal_generator | QNN_DLC | float | Qualcomm® SA8775P | 122.39 ms | 0 - 1756 MB | NPU
68
+ | proposal_generator | QNN_DLC | float | Qualcomm® SA8775P | 122.39 ms | 0 - 1756 MB | NPU
69
+ | proposal_generator | QNN_DLC | float | Qualcomm® QCS9075 | 119.033 ms | 7 - 71 MB | NPU
70
+ | proposal_generator | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 151.505 ms | 7 - 2739 MB | NPU
71
+ | proposal_generator | QNN_DLC | float | Qualcomm® SA7255P | 353.892 ms | 0 - 1756 MB | NPU
72
+ | proposal_generator | QNN_DLC | float | Qualcomm® SA8295P | 125.974 ms | 0 - 1430 MB | NPU
73
+ | proposal_generator | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 53.244 ms | 0 - 1510 MB | NPU
74
+ | roi_head | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 99.642 ms | 51 - 749 MB | NPU
75
+ | roi_head | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 125.168 ms | 28 - 719 MB | NPU
76
+ | roi_head | QNN_DLC | float | Snapdragon® X2 Elite | 96.983 ms | 52 - 52 MB | NPU
77
+ | roi_head | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 178.224 ms | 46 - 893 MB | NPU
78
+ | roi_head | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 590.646 ms | 39 - 734 MB | NPU
79
+ | roi_head | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 249.643 ms | 52 - 58 MB | NPU
80
+ | roi_head | QNN_DLC | float | Qualcomm® SA8775P | 267.888 ms | 49 - 923 MB | NPU
81
+ | roi_head | QNN_DLC | float | Qualcomm® SA8775P | 267.888 ms | 49 - 923 MB | NPU
82
+ | roi_head | QNN_DLC | float | Qualcomm® SA8775P | 267.888 ms | 49 - 923 MB | NPU
83
+ | roi_head | QNN_DLC | float | Qualcomm® QCS9075 | 342.162 ms | 52 - 106 MB | NPU
84
+ | roi_head | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 313.188 ms | 39 - 957 MB | NPU
85
+ | roi_head | QNN_DLC | float | Qualcomm® SA7255P | 590.646 ms | 39 - 734 MB | NPU
86
+ | roi_head | QNN_DLC | float | Qualcomm® SA8295P | 307.476 ms | 49 - 846 MB | NPU
87
+ | roi_head | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 125.168 ms | 28 - 719 MB | NPU
88
 
89
  ## License
90
  * The license for the original implementation of MaskRCNN can be found
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.52.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
@@ -7,7 +7,7 @@
7
  "tool_versions": {
8
  "qairt": "2.45.0.260326154327"
9
  },
10
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/maskrcnn/releases/v0.52.0/maskrcnn-qnn_dlc-float.zip"
11
  }
12
  }
13
  }
 
1
  {
2
+ "version": "0.53.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
 
7
  "tool_versions": {
8
  "qairt": "2.45.0.260326154327"
9
  },
10
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/maskrcnn/releases/v0.53.0/maskrcnn-qnn_dlc-float.zip"
11
  }
12
  }
13
  }