Hugging Face's logo

qualcomm
/
MaskRCNN

Image Segmentation
PyTorch
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
8612c21
·
verified ·
1 Parent(s): 7c53ddc

v0.49.1

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.49.1 for changelog.

Files changed (1) hide show
  1. README.md +26 -26
README.md CHANGED
@@ -14,7 +14,7 @@ pipeline_tag: image-segmentation
14
  Mask R-CNN is a machine learning model that extends Faster R-CNN to perform instance segmentation by detecting objects in an image while simultaneously generating a high-quality segmentation mask for each instance. It adds a branch for predicting segmentation masks in parallel with the existing branch for bounding box recognition.
15
 
16
  This is based on the implementation of MaskRCNN found [here](https://github.com/pytorch/vision).
17
- 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/main/qai_hub_models/models/maskrcnn) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
18
 
19
  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.
20
 
@@ -27,21 +27,21 @@ Below are pre-exported model assets ready for deployment.
27
 
28
  | Runtime | Precision | Chipset | SDK Versions | Download |
29
  |---|---|---|---|---|
30
- | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/maskrcnn/releases/v0.48.0/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
 
34
 
35
  ### Option 2: Export with Custom Configurations
36
 
37
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/maskrcnn) Python library to compile and export the model with your own:
38
  - Custom weights (e.g., fine-tuned checkpoints)
39
  - Custom input shapes
40
  - Target device and runtime configurations
41
 
42
  This option is ideal if you need to customize the model beyond the default configuration provided here.
43
 
44
- See our repository for [MaskRCNN on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/maskrcnn) for usage instructions.
45
 
46
  ## Model Details
47
 
@@ -57,28 +57,28 @@ 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
- | MaskRCNNProposalGenerator | QNN_DLC | float | Snapdragon® X2 Elite | 58.538 ms | 7 - 7 MB | NPU
61
- | MaskRCNNProposalGenerator | QNN_DLC | float | Snapdragon® X Elite | 139.069 ms | 7 - 7 MB | NPU
62
- | MaskRCNNProposalGenerator | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 107.556 ms | 7 - 1397 MB | NPU
63
- | MaskRCNNProposalGenerator | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 415.682 ms | 1 - 1194 MB | NPU
64
- | MaskRCNNProposalGenerator | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 148.984 ms | 7 - 10 MB | NPU
65
- | MaskRCNNProposalGenerator | QNN_DLC | float | Qualcomm® SA8775P | 167.04 ms | 1 - 1195 MB | NPU
66
- | MaskRCNNProposalGenerator | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 209.409 ms | 7 - 1358 MB | NPU
67
- | MaskRCNNProposalGenerator | QNN_DLC | float | Qualcomm® SA7255P | 415.682 ms | 1 - 1194 MB | NPU
68
- | MaskRCNNProposalGenerator | QNN_DLC | float | Qualcomm® SA8295P | 168.867 ms | 0 - 1139 MB | NPU
69
- | MaskRCNNProposalGenerator | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 69.508 ms | 7 - 1305 MB | NPU
70
- | MaskRCNNProposalGenerator | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 54.824 ms | 7 - 1326 MB | NPU
71
- | MaskRCNNROIHead | QNN_DLC | float | Snapdragon® X2 Elite | 100.247 ms | 52 - 52 MB | NPU
72
- | MaskRCNNROIHead | QNN_DLC | float | Snapdragon® X Elite | 239.818 ms | 52 - 52 MB | NPU
73
- | MaskRCNNROIHead | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 180.07 ms | 12 - 892 MB | NPU
74
- | MaskRCNNROIHead | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 581.756 ms | 45 - 845 MB | NPU
75
- | MaskRCNNROIHead | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 240.254 ms | 39 - 42 MB | NPU
76
- | MaskRCNNROIHead | QNN_DLC | float | Qualcomm® SA8775P | 268.815 ms | 42 - 844 MB | NPU
77
- | MaskRCNNROIHead | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 346.463 ms | 39 - 941 MB | NPU
78
- | MaskRCNNROIHead | QNN_DLC | float | Qualcomm® SA7255P | 581.756 ms | 45 - 845 MB | NPU
79
- | MaskRCNNROIHead | QNN_DLC | float | Qualcomm® SA8295P | 307.228 ms | 46 - 971 MB | NPU
80
- | MaskRCNNROIHead | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 125.821 ms | 23 - 813 MB | NPU
81
- | MaskRCNNROIHead | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 96.944 ms | 51 - 854 MB | NPU
82
 
83
  ## License
84
  * The license for the original implementation of MaskRCNN can be found
 
14
  Mask R-CNN is a machine learning model that extends Faster R-CNN to perform instance segmentation by detecting objects in an image while simultaneously generating a high-quality segmentation mask for each instance. It adds a branch for predicting segmentation masks in parallel with the existing branch for bounding box recognition.
15
 
16
  This is based on the implementation of MaskRCNN found [here](https://github.com/pytorch/vision).
17
+ 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/tree/v0.49.1/qai_hub_models/models/maskrcnn) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
18
 
19
  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.
20
 
 
27
 
28
  | Runtime | Precision | Chipset | SDK Versions | Download |
29
  |---|---|---|---|---|
30
+ | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/maskrcnn/releases/v0.49.1/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
 
34
 
35
  ### Option 2: Export with Custom Configurations
36
 
37
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/tree/v0.49.1/qai_hub_models/models/maskrcnn) Python library to compile and export the model with your own:
38
  - Custom weights (e.g., fine-tuned checkpoints)
39
  - Custom input shapes
40
  - Target device and runtime configurations
41
 
42
  This option is ideal if you need to customize the model beyond the default configuration provided here.
43
 
44
+ See our repository for [MaskRCNN on GitHub](https://github.com/qualcomm/ai-hub-models/tree/v0.49.1/qai_hub_models/models/maskrcnn) for usage instructions.
45
 
46
  ## Model Details
47
 
 
57
  ## Performance Summary
58
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
59
  |---|---|---|---|---|---|---
60
+ | MaskRCNNProposalGenerator | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 56.939 ms | 7 - 1326 MB | NPU
61
+ | MaskRCNNProposalGenerator | QNN_DLC | float | Snapdragon® X2 Elite | 58.441 ms | 7 - 7 MB | NPU
62
+ | MaskRCNNProposalGenerator | QNN_DLC | float | Snapdragon® X Elite | 139.008 ms | 7 - 7 MB | NPU
63
+ | MaskRCNNProposalGenerator | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 105.679 ms | 7 - 1393 MB | NPU
64
+ | MaskRCNNProposalGenerator | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 415.448 ms | 2 - 1195 MB | NPU
65
+ | MaskRCNNProposalGenerator | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 148.486 ms | 7 - 751 MB | NPU
66
+ | MaskRCNNProposalGenerator | QNN_DLC | float | Qualcomm® SA8775P | 167.193 ms | 1 - 1195 MB | NPU
67
+ | MaskRCNNProposalGenerator | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 210.601 ms | 8 - 1353 MB | NPU
68
+ | MaskRCNNProposalGenerator | QNN_DLC | float | Qualcomm® SA7255P | 415.448 ms | 2 - 1195 MB | NPU
69
+ | MaskRCNNProposalGenerator | QNN_DLC | float | Qualcomm® SA8295P | 168.736 ms | 0 - 1139 MB | NPU
70
+ | MaskRCNNProposalGenerator | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 71.498 ms | 7 - 1304 MB | NPU
71
+ | MaskRCNNROIHead | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 93.517 ms | 51 - 854 MB | NPU
72
+ | MaskRCNNROIHead | QNN_DLC | float | Snapdragon® X2 Elite | 99.886 ms | 52 - 52 MB | NPU
73
+ | MaskRCNNROIHead | QNN_DLC | float | Snapdragon® X Elite | 235.822 ms | 52 - 52 MB | NPU
74
+ | MaskRCNNROIHead | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 180.185 ms | 49 - 929 MB | NPU
75
+ | MaskRCNNROIHead | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 596.745 ms | 49 - 849 MB | NPU
76
+ | MaskRCNNROIHead | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 242.165 ms | 52 - 54 MB | NPU
77
+ | MaskRCNNROIHead | QNN_DLC | float | Qualcomm® SA8775P | 1129.878 ms | 40 - 841 MB | NPU
78
+ | MaskRCNNROIHead | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 326.792 ms | 39 - 940 MB | NPU
79
+ | MaskRCNNROIHead | QNN_DLC | float | Qualcomm® SA7255P | 596.745 ms | 49 - 849 MB | NPU
80
+ | MaskRCNNROIHead | QNN_DLC | float | Qualcomm® SA8295P | 302.095 ms | 49 - 974 MB | NPU
81
+ | MaskRCNNROIHead | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 126.714 ms | 34 - 824 MB | NPU
82
 
83
  ## License
84
  * The license for the original implementation of MaskRCNN can be found