qaihm-bot commited on
Commit
1d5e2d6
·
verified ·
1 Parent(s): b107233

See https://github.com/qualcomm/ai-hub-models/releases/v0.66.0 for changelog.

Files changed (2) hide show
  1. README.md +7 -7
  2. release_assets.json +5 -5
README.md CHANGED
@@ -15,7 +15,7 @@ pipeline_tag: image-segmentation
15
  SAM 2, the successor to Meta's Segment Anything Model (SAM), is a cutting-edge tool designed for comprehensive object segmentation in both images and videos. It excels in handling complex visual data through a unified, promptable model architecture that supports real-time processing and zero-shot generalization.
16
 
17
  This is based on the implementation of Segment-Anything-Model-2 found [here](https://github.com/facebookresearch/sam2).
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/v0.65.0/src/qai_hub_models/models/sam2) 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
 
@@ -28,24 +28,24 @@ Below are pre-exported model assets ready for deployment.
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
- | ONNX | w8a8 | Universal | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/releases/v0.65.0/sam2-onnx-w8a8.zip)
32
- | QNN_DLC | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/releases/v0.65.0/sam2-qnn_dlc-float.zip)
33
- | QNN_DLC | w8a8 | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/releases/v0.65.0/sam2-qnn_dlc-w8a8.zip)
34
- | TFLITE | w8a8 | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/releases/v0.65.0/sam2-tflite-w8a8.zip)
35
 
36
  For more device-specific assets and performance metrics, visit **[Segment-Anything-Model-2 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/sam2)**.
37
 
38
 
39
  ### Option 2: Export with Custom Configurations
40
 
41
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.65.0/src/qai_hub_models/models/sam2) Python library to compile and export the model with your own:
42
  - Custom weights (e.g., fine-tuned checkpoints)
43
  - Custom input shapes
44
  - Target device and runtime configurations
45
 
46
  This option is ideal if you need to customize the model beyond the default configuration provided here.
47
 
48
- See our repository for [Segment-Anything-Model-2 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.65.0/src/qai_hub_models/models/sam2) for usage instructions.
49
 
50
  ## Model Details
51
 
 
15
  SAM 2, the successor to Meta's Segment Anything Model (SAM), is a cutting-edge tool designed for comprehensive object segmentation in both images and videos. It excels in handling complex visual data through a unified, promptable model architecture that supports real-time processing and zero-shot generalization.
16
 
17
  This is based on the implementation of Segment-Anything-Model-2 found [here](https://github.com/facebookresearch/sam2).
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/v0.66.0/src/qai_hub_models/models/sam2) 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
 
 
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
+ | ONNX | w8a8 | Universal | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/releases/v0.66.0/sam2-onnx-w8a8.zip)
32
+ | QNN_DLC | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/releases/v0.66.0/sam2-qnn_dlc-float.zip)
33
+ | QNN_DLC | w8a8 | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/releases/v0.66.0/sam2-qnn_dlc-w8a8.zip)
34
+ | TFLITE | w8a8 | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/releases/v0.66.0/sam2-tflite-w8a8.zip)
35
 
36
  For more device-specific assets and performance metrics, visit **[Segment-Anything-Model-2 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/sam2)**.
37
 
38
 
39
  ### Option 2: Export with Custom Configurations
40
 
41
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.66.0/src/qai_hub_models/models/sam2) Python library to compile and export the model with your own:
42
  - Custom weights (e.g., fine-tuned checkpoints)
43
  - Custom input shapes
44
  - Target device and runtime configurations
45
 
46
  This option is ideal if you need to customize the model beyond the default configuration provided here.
47
 
48
+ See our repository for [Segment-Anything-Model-2 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.66.0/src/qai_hub_models/models/sam2) for usage instructions.
49
 
50
  ## Model Details
51
 
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.65.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
@@ -7,7 +7,7 @@
7
  "tool_versions": {
8
  "qairt": "2.50.0.260828221209"
9
  },
10
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/releases/v0.65.0/sam2-qnn_dlc-float.zip"
11
  }
12
  }
13
  },
@@ -18,19 +18,19 @@
18
  "qairt": "2.50.0.260828221209",
19
  "onnx_runtime": "1.30.0"
20
  },
21
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/releases/v0.65.0/sam2-onnx-w8a8.zip"
22
  },
23
  "qnn_dlc": {
24
  "tool_versions": {
25
  "qairt": "2.50.0.260828221209"
26
  },
27
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/releases/v0.65.0/sam2-qnn_dlc-w8a8.zip"
28
  },
29
  "tflite": {
30
  "tool_versions": {
31
  "qairt": "2.50.0.260828221209"
32
  },
33
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/releases/v0.65.0/sam2-tflite-w8a8.zip"
34
  }
35
  }
36
  }
 
1
  {
2
+ "version": "0.66.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
 
7
  "tool_versions": {
8
  "qairt": "2.50.0.260828221209"
9
  },
10
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/releases/v0.66.0/sam2-qnn_dlc-float.zip"
11
  }
12
  }
13
  },
 
18
  "qairt": "2.50.0.260828221209",
19
  "onnx_runtime": "1.30.0"
20
  },
21
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/releases/v0.66.0/sam2-onnx-w8a8.zip"
22
  },
23
  "qnn_dlc": {
24
  "tool_versions": {
25
  "qairt": "2.50.0.260828221209"
26
  },
27
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/releases/v0.66.0/sam2-qnn_dlc-w8a8.zip"
28
  },
29
  "tflite": {
30
  "tool_versions": {
31
  "qairt": "2.50.0.260828221209"
32
  },
33
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/releases/v0.66.0/sam2-tflite-w8a8.zip"
34
  }
35
  }
36
  }