qaihm-bot commited on
Commit
4b65a8c
·
verified ·
1 Parent(s): 55ea6a9

See https://github.com/qualcomm/ai-hub-models/releases/v0.52.0 for changelog.

Files changed (3) hide show
  1. LICENSE +1 -1
  2. README.md +18 -18
  3. release_assets.json +4 -4
LICENSE CHANGED
@@ -1 +1 @@
1
- The license of the original trained model can be found at https://github.com/CASIA-IVA-Lab/FastSAM/blob/main/LICENSE.
 
1
+ The license of the original trained model can be found at https://github.com/CASIA-LMC-Lab/FastSAM/blob/main/LICENSE.
README.md CHANGED
@@ -13,7 +13,7 @@ pipeline_tag: image-segmentation
13
 
14
  The Fast Segment Anything Model (FastSAM) is a novel, real-time CNN-based solution for the Segment Anything task. This task is designed to segment any object within an image based on various possible user interaction prompts. The model performs competitively despite significantly reduced computation, making it a practical choice for a variety of vision tasks.
15
 
16
- This is based on the implementation of FastSam-X found [here](https://github.com/CASIA-IVA-Lab/FastSAM).
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/src/qai_hub_models/models/fastsam_x) 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.
@@ -27,9 +27,9 @@ Below are pre-exported model assets ready for deployment.
27
 
28
  | Runtime | Precision | Chipset | SDK Versions | Download |
29
  |---|---|---|---|---|
30
- | ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fastsam_x/releases/v0.51.0/fastsam_x-onnx-float.zip)
31
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fastsam_x/releases/v0.51.0/fastsam_x-qnn_dlc-float.zip)
32
- | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fastsam_x/releases/v0.51.0/fastsam_x-tflite-float.zip)
33
 
34
  For more device-specific assets and performance metrics, visit **[FastSam-X on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/fastsam_x)**.
35
 
@@ -66,18 +66,18 @@ See our repository for [FastSam-X on GitHub](https://github.com/qualcomm/ai-hub-
66
  | FastSam-X | ONNX | float | Qualcomm® QCS8550 (Proxy) | 46.81 ms | 0 - 158 MB | NPU
67
  | FastSam-X | ONNX | float | Qualcomm® QCS9075 | 73.46 ms | 10 - 17 MB | NPU
68
  | FastSam-X | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 27.449 ms | 12 - 255 MB | NPU
69
- | FastSam-X | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 17.634 ms | 5 - 236 MB | NPU
70
- | FastSam-X | QNN_DLC | float | Snapdragon® X2 Elite | 23.271 ms | 5 - 5 MB | NPU
71
- | FastSam-X | QNN_DLC | float | Snapdragon® X Elite | 43.963 ms | 5 - 5 MB | NPU
72
- | FastSam-X | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 32.942 ms | 3 - 300 MB | NPU
73
- | FastSam-X | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 279.839 ms | 0 - 215 MB | NPU
74
- | FastSam-X | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 42.673 ms | 5 - 6 MB | NPU
75
- | FastSam-X | QNN_DLC | float | Qualcomm® SA8775P | 68.515 ms | 0 - 214 MB | NPU
76
- | FastSam-X | QNN_DLC | float | Qualcomm® QCS9075 | 71.366 ms | 7 - 17 MB | NPU
77
- | FastSam-X | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 91.984 ms | 4 - 387 MB | NPU
78
- | FastSam-X | QNN_DLC | float | Qualcomm® SA7255P | 279.839 ms | 0 - 215 MB | NPU
79
- | FastSam-X | QNN_DLC | float | Qualcomm® SA8295P | 77.736 ms | 0 - 298 MB | NPU
80
- | FastSam-X | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 25.388 ms | 0 - 222 MB | NPU
81
  | FastSam-X | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 17.677 ms | 4 - 264 MB | NPU
82
  | FastSam-X | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 32.619 ms | 4 - 416 MB | NPU
83
  | FastSam-X | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 279.343 ms | 4 - 258 MB | NPU
@@ -91,11 +91,11 @@ See our repository for [FastSam-X on GitHub](https://github.com/qualcomm/ai-hub-
91
 
92
  ## License
93
  * The license for the original implementation of FastSam-X can be found
94
- [here](https://github.com/CASIA-IVA-Lab/FastSAM/blob/main/LICENSE).
95
 
96
  ## References
97
  * [Fast Segment Anything](https://arxiv.org/abs/2306.12156)
98
- * [Source Model Implementation](https://github.com/CASIA-IVA-Lab/FastSAM)
99
 
100
  ## Community
101
  * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
 
13
 
14
  The Fast Segment Anything Model (FastSAM) is a novel, real-time CNN-based solution for the Segment Anything task. This task is designed to segment any object within an image based on various possible user interaction prompts. The model performs competitively despite significantly reduced computation, making it a practical choice for a variety of vision tasks.
15
 
16
+ This is based on the implementation of FastSam-X found [here](https://github.com/CASIA-LMC-Lab/FastSAM).
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/src/qai_hub_models/models/fastsam_x) 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.
 
27
 
28
  | Runtime | Precision | Chipset | SDK Versions | Download |
29
  |---|---|---|---|---|
30
+ | ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fastsam_x/releases/v0.52.0/fastsam_x-onnx-float.zip)
31
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fastsam_x/releases/v0.52.0/fastsam_x-qnn_dlc-float.zip)
32
+ | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fastsam_x/releases/v0.52.0/fastsam_x-tflite-float.zip)
33
 
34
  For more device-specific assets and performance metrics, visit **[FastSam-X on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/fastsam_x)**.
35
 
 
66
  | FastSam-X | ONNX | float | Qualcomm® QCS8550 (Proxy) | 46.81 ms | 0 - 158 MB | NPU
67
  | FastSam-X | ONNX | float | Qualcomm® QCS9075 | 73.46 ms | 10 - 17 MB | NPU
68
  | FastSam-X | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 27.449 ms | 12 - 255 MB | NPU
69
+ | FastSam-X | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 17.621 ms | 5 - 236 MB | NPU
70
+ | FastSam-X | QNN_DLC | float | Snapdragon® X2 Elite | 23.288 ms | 5 - 5 MB | NPU
71
+ | FastSam-X | QNN_DLC | float | Snapdragon® X Elite | 43.985 ms | 5 - 5 MB | NPU
72
+ | FastSam-X | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 32.921 ms | 4 - 303 MB | NPU
73
+ | FastSam-X | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 279.887 ms | 1 - 215 MB | NPU
74
+ | FastSam-X | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 42.903 ms | 5 - 7 MB | NPU
75
+ | FastSam-X | QNN_DLC | float | Qualcomm® SA8775P | 68.551 ms | 0 - 213 MB | NPU
76
+ | FastSam-X | QNN_DLC | float | Qualcomm® QCS9075 | 70.797 ms | 5 - 15 MB | NPU
77
+ | FastSam-X | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 91.601 ms | 4 - 385 MB | NPU
78
+ | FastSam-X | QNN_DLC | float | Qualcomm® SA7255P | 279.887 ms | 1 - 215 MB | NPU
79
+ | FastSam-X | QNN_DLC | float | Qualcomm® SA8295P | 77.761 ms | 0 - 298 MB | NPU
80
+ | FastSam-X | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 25.398 ms | 0 - 223 MB | NPU
81
  | FastSam-X | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 17.677 ms | 4 - 264 MB | NPU
82
  | FastSam-X | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 32.619 ms | 4 - 416 MB | NPU
83
  | FastSam-X | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 279.343 ms | 4 - 258 MB | NPU
 
91
 
92
  ## License
93
  * The license for the original implementation of FastSam-X can be found
94
+ [here](https://github.com/CASIA-LMC-Lab/FastSAM/blob/main/LICENSE).
95
 
96
  ## References
97
  * [Fast Segment Anything](https://arxiv.org/abs/2306.12156)
98
+ * [Source Model Implementation](https://github.com/CASIA-LMC-Lab/FastSAM)
99
 
100
  ## Community
101
  * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.51.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
@@ -8,20 +8,20 @@
8
  "qairt": "2.45.0.260326154327",
9
  "litert": "1.4.2"
10
  },
11
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fastsam_x/releases/v0.51.0/fastsam_x-tflite-float.zip"
12
  },
13
  "qnn_dlc": {
14
  "tool_versions": {
15
  "qairt": "2.45.0.260326154327"
16
  },
17
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fastsam_x/releases/v0.51.0/fastsam_x-qnn_dlc-float.zip"
18
  },
19
  "onnx": {
20
  "tool_versions": {
21
  "qairt": "2.42.0.251225135753_193295",
22
  "onnx_runtime": "1.24.3"
23
  },
24
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fastsam_x/releases/v0.51.0/fastsam_x-onnx-float.zip"
25
  }
26
  }
27
  }
 
1
  {
2
+ "version": "0.52.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
 
8
  "qairt": "2.45.0.260326154327",
9
  "litert": "1.4.2"
10
  },
11
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fastsam_x/releases/v0.52.0/fastsam_x-tflite-float.zip"
12
  },
13
  "qnn_dlc": {
14
  "tool_versions": {
15
  "qairt": "2.45.0.260326154327"
16
  },
17
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fastsam_x/releases/v0.52.0/fastsam_x-qnn_dlc-float.zip"
18
  },
19
  "onnx": {
20
  "tool_versions": {
21
  "qairt": "2.42.0.251225135753_193295",
22
  "onnx_runtime": "1.24.3"
23
  },
24
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fastsam_x/releases/v0.52.0/fastsam_x-onnx-float.zip"
25
  }
26
  }
27
  }