Hugging Face's logo

qualcomm
/
ResNet34-SSD

Object Detection
PyTorch
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
a86ce34
·
verified ·
1 Parent(s): 91e66b3

v0.64.0

Browse files

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

Files changed (2) hide show
  1. README.md +47 -44
  2. release_assets.json +5 -5
README.md CHANGED
@@ -14,7 +14,7 @@ pipeline_tag: object-detection
14
  ResNet34-SSD is a single-stage object detection model that integrates the ResNet34 backbone with the SSD (Single Shot MultiBox Detector) framework. It is optimized for real-time detection tasks and supports multiple deployment backends including PyTorch, TensorFlow, and ONNX.
15
 
16
  This is based on the implementation of ResNet34-SSD found [here](https://github.com/mlcommons/inference/tree/33894a19c4af6207f7cfdda75f84570f04836de5/vision/classification_and_detection).
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/v0.63.0/src/qai_hub_models/models/resnet34_ssd1200) 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
 
@@ -27,23 +27,23 @@ Below are pre-exported model assets ready for deployment.
27
 
28
  | Runtime | Precision | Chipset | SDK Versions | Download |
29
  |---|---|---|---|---|
30
- | ONNX | float | Universal | QAIRT 2.50, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet34_ssd1200/releases/v0.63.0/resnet34_ssd1200-onnx-float.zip)
31
- | QNN_DLC | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet34_ssd1200/releases/v0.63.0/resnet34_ssd1200-qnn_dlc-float.zip)
32
- | TFLITE | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet34_ssd1200/releases/v0.63.0/resnet34_ssd1200-tflite-float.zip)
33
 
34
  For more device-specific assets and performance metrics, visit **[ResNet34-SSD on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/resnet34_ssd1200)**.
35
 
36
 
37
  ### Option 2: Export with Custom Configurations
38
 
39
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/resnet34_ssd1200) Python library to compile and export the model with your own:
40
  - Custom weights (e.g., fine-tuned checkpoints)
41
  - Custom input shapes
42
  - Target device and runtime configurations
43
 
44
  This option is ideal if you need to customize the model beyond the default configuration provided here.
45
 
46
- See our repository for [ResNet34-SSD on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/resnet34_ssd1200) for usage instructions.
47
 
48
  ## Model Details
49
 
@@ -58,44 +58,47 @@ See our repository for [ResNet34-SSD on GitHub](https://github.com/qualcomm/ai-h
58
  ## Performance Summary
59
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
60
  |---|---|---|---|---|---|---
61
- | ResNet34-SSD | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 31.98 ms | 2 - 277 MB | NPU
62
- | ResNet34-SSD | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 42.665 ms | 1 - 250 MB | NPU
63
- | ResNet34-SSD | ONNX | float | Snapdragon® X2 Elite | 40.254 ms | 17 - 17 MB | NPU
64
- | ResNet34-SSD | ONNX | float | Snapdragon® X Elite | 68.287 ms | 28 - 28 MB | NPU
65
- | ResNet34-SSD | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 50.557 ms | 1 - 364 MB | NPU
66
- | ResNet34-SSD | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 112.708 ms | 16 - 303 MB | NPU
67
- | ResNet34-SSD | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 125.756 ms | 16 - 37 MB | NPU
68
- | ResNet34-SSD | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 68.202 ms | 5 - 336 MB | NPU
69
- | ResNet34-SSD | ONNX | float | Qualcomm® QCS8450 | 112.708 ms | 16 - 303 MB | NPU
70
- | ResNet34-SSD | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 114.807 ms | 16 - 36 MB | NPU
71
- | ResNet34-SSD | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 68.287 ms | 28 - 28 MB | NPU
72
- | ResNet34-SSD | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 42.665 ms | 1 - 250 MB | NPU
73
- | ResNet34-SSD | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 45.702 ms | 0 - 289 MB | NPU
74
- | ResNet34-SSD | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 43.697 ms | 0 - 243 MB | NPU
75
- | ResNet34-SSD | QNN_DLC | float | Snapdragon® X2 Elite | 49.971 ms | 17 - 17 MB | NPU
76
- | ResNet34-SSD | QNN_DLC | float | Snapdragon® X Elite | 76.175 ms | 17 - 17 MB | NPU
77
- | ResNet34-SSD | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 55.414 ms | 0 - 352 MB | NPU
78
- | ResNet34-SSD | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 118.595 ms | 3 - 314 MB | NPU
79
- | ResNet34-SSD | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 128.392 ms | 17 - 36 MB | NPU
80
- | ResNet34-SSD | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 75.56 ms | 17 - 416 MB | NPU
81
- | ResNet34-SSD | QNN_DLC | float | Qualcomm® QCS8450 | 118.595 ms | 3 - 314 MB | NPU
82
- | ResNet34-SSD | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 118.694 ms | 17 - 35 MB | NPU
83
- | ResNet34-SSD | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 76.175 ms | 17 - 17 MB | NPU
84
- | ResNet34-SSD | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 43.697 ms | 0 - 243 MB | NPU
85
- | ResNet34-SSD | QNN_DLC | float | Qualcomm® SA8295P | 141.144 ms | 0 - 210 MB | NPU
86
- | ResNet34-SSD | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 33.314 ms | 0 - 303 MB | NPU
87
- | ResNet34-SSD | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 39.825 ms | 1 - 267 MB | NPU
88
- | ResNet34-SSD | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 50.411 ms | 0 - 390 MB | NPU
89
- | ResNet34-SSD | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 122.781 ms | 1 - 330 MB | NPU
90
- | ResNet34-SSD | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 121.722 ms | 0 - 63 MB | NPU
91
- | ResNet34-SSD | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 70.36 ms | 1 - 3 MB | NPU
92
- | ResNet34-SSD | TFLITE | float | Qualcomm® SA8775P | 112.957 ms | 1 - 259 MB | NPU
93
- | ResNet34-SSD | TFLITE | float | Qualcomm® SA8650P | 112.957 ms | 1 - 259 MB | NPU
94
- | ResNet34-SSD | TFLITE | float | Qualcomm® SA8255P | 112.957 ms | 1 - 259 MB | NPU
95
- | ResNet34-SSD | TFLITE | float | Qualcomm® QCS8450 | 122.781 ms | 1 - 330 MB | NPU
96
- | ResNet34-SSD | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 113.315 ms | 0 - 63 MB | NPU
97
- | ResNet34-SSD | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 39.825 ms | 1 - 267 MB | NPU
98
- | ResNet34-SSD | TFLITE | float | Qualcomm® SA8295P | 125.091 ms | 1 - 211 MB | NPU
 
 
 
99
 
100
  ## License
101
  * The license for the original implementation of ResNet34-SSD can be found
 
14
  ResNet34-SSD is a single-stage object detection model that integrates the ResNet34 backbone with the SSD (Single Shot MultiBox Detector) framework. It is optimized for real-time detection tasks and supports multiple deployment backends including PyTorch, TensorFlow, and ONNX.
15
 
16
  This is based on the implementation of ResNet34-SSD found [here](https://github.com/mlcommons/inference/tree/33894a19c4af6207f7cfdda75f84570f04836de5/vision/classification_and_detection).
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/v0.64.0/src/qai_hub_models/models/resnet34_ssd1200) 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
+ | ONNX | float | Universal | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet34_ssd1200/releases/v0.64.0/resnet34_ssd1200-onnx-float.zip)
31
+ | QNN_DLC | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet34_ssd1200/releases/v0.64.0/resnet34_ssd1200-qnn_dlc-float.zip)
32
+ | TFLITE | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet34_ssd1200/releases/v0.64.0/resnet34_ssd1200-tflite-float.zip)
33
 
34
  For more device-specific assets and performance metrics, visit **[ResNet34-SSD on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/resnet34_ssd1200)**.
35
 
36
 
37
  ### Option 2: Export with Custom Configurations
38
 
39
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.64.0/src/qai_hub_models/models/resnet34_ssd1200) Python library to compile and export the model with your own:
40
  - Custom weights (e.g., fine-tuned checkpoints)
41
  - Custom input shapes
42
  - Target device and runtime configurations
43
 
44
  This option is ideal if you need to customize the model beyond the default configuration provided here.
45
 
46
+ See our repository for [ResNet34-SSD on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.64.0/src/qai_hub_models/models/resnet34_ssd1200) for usage instructions.
47
 
48
  ## Model Details
49
 
 
58
  ## Performance Summary
59
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
60
  |---|---|---|---|---|---|---
61
+ | ResNet34-SSD | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 32.165 ms | 1 - 277 MB | NPU
62
+ | ResNet34-SSD | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 42.685 ms | 1 - 250 MB | NPU
63
+ | ResNet34-SSD | ONNX | float | Snapdragon® X2 Elite | 40.125 ms | 17 - 17 MB | NPU
64
+ | ResNet34-SSD | ONNX | float | Snapdragon® X Elite | 68.228 ms | 28 - 28 MB | NPU
65
+ | ResNet34-SSD | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 50.488 ms | 18 - 384 MB | NPU
66
+ | ResNet34-SSD | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 121.127 ms | 1 - 288 MB | NPU
67
+ | ResNet34-SSD | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 125.64 ms | 16 - 37 MB | NPU
68
+ | ResNet34-SSD | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 67.241 ms | 17 - 20 MB | NPU
69
+ | ResNet34-SSD | ONNX | float | Qualcomm® QCS8450 | 121.127 ms | 1 - 288 MB | NPU
70
+ | ResNet34-SSD | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 114.573 ms | 16 - 36 MB | NPU
71
+ | ResNet34-SSD | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 68.228 ms | 28 - 28 MB | NPU
72
+ | ResNet34-SSD | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 42.685 ms | 1 - 250 MB | NPU
73
+ | ResNet34-SSD | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 45.559 ms | 4 - 294 MB | NPU
74
+ | ResNet34-SSD | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 43.65 ms | 15 - 257 MB | NPU
75
+ | ResNet34-SSD | QNN_DLC | float | Snapdragon® X2 Elite | 49.926 ms | 17 - 17 MB | NPU
76
+ | ResNet34-SSD | QNN_DLC | float | Snapdragon® X Elite | 76.25 ms | 17 - 17 MB | NPU
77
+ | ResNet34-SSD | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 55.524 ms | 16 - 368 MB | NPU
78
+ | ResNet34-SSD | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 120.239 ms | 4 - 315 MB | NPU
79
+ | ResNet34-SSD | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 128.466 ms | 17 - 36 MB | NPU
80
+ | ResNet34-SSD | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 75.265 ms | 17 - 427 MB | NPU
81
+ | ResNet34-SSD | QNN_DLC | float | Qualcomm® SA8775P | 117.164 ms | 16 - 251 MB | NPU
82
+ | ResNet34-SSD | QNN_DLC | float | Qualcomm® SA8650P | 117.164 ms | 16 - 251 MB | NPU
83
+ | ResNet34-SSD | QNN_DLC | float | Qualcomm® SA8255P | 117.164 ms | 16 - 251 MB | NPU
84
+ | ResNet34-SSD | QNN_DLC | float | Qualcomm® QCS8450 | 120.239 ms | 4 - 315 MB | NPU
85
+ | ResNet34-SSD | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 118.219 ms | 17 - 35 MB | NPU
86
+ | ResNet34-SSD | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 76.25 ms | 17 - 17 MB | NPU
87
+ | ResNet34-SSD | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 43.65 ms | 15 - 257 MB | NPU
88
+ | ResNet34-SSD | QNN_DLC | float | Qualcomm® SA8295P | 141.167 ms | 0 - 210 MB | NPU
89
+ | ResNet34-SSD | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 33.39 ms | 0 - 303 MB | NPU
90
+ | ResNet34-SSD | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 40.059 ms | 1 - 265 MB | NPU
91
+ | ResNet34-SSD | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 50.656 ms | 9 - 402 MB | NPU
92
+ | ResNet34-SSD | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 116.209 ms | 1 - 330 MB | NPU
93
+ | ResNet34-SSD | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 121.697 ms | 0 - 63 MB | NPU
94
+ | ResNet34-SSD | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 72.434 ms | 1 - 4 MB | NPU
95
+ | ResNet34-SSD | TFLITE | float | Qualcomm® SA8775P | 112.908 ms | 1 - 260 MB | NPU
96
+ | ResNet34-SSD | TFLITE | float | Qualcomm® SA8650P | 112.908 ms | 1 - 260 MB | NPU
97
+ | ResNet34-SSD | TFLITE | float | Qualcomm® SA8255P | 112.908 ms | 1 - 260 MB | NPU
98
+ | ResNet34-SSD | TFLITE | float | Qualcomm® QCS8450 | 116.209 ms | 1 - 330 MB | NPU
99
+ | ResNet34-SSD | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 113.351 ms | 0 - 63 MB | NPU
100
+ | ResNet34-SSD | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 40.059 ms | 1 - 265 MB | NPU
101
+ | ResNet34-SSD | TFLITE | float | Qualcomm® SA8295P | 125.111 ms | 1 - 212 MB | NPU
102
 
103
  ## License
104
  * The license for the original implementation of ResNet34-SSD can be found
release_assets.json CHANGED
@@ -1,26 +1,26 @@
1
  {
2
- "version": "0.63.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
6
  "onnx": {
7
  "tool_versions": {
8
  "qairt": "2.50.0.260828221209",
9
- "onnx_runtime": "1.27.1"
10
  },
11
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet34_ssd1200/releases/v0.63.0/resnet34_ssd1200-onnx-float.zip"
12
  },
13
  "qnn_dlc": {
14
  "tool_versions": {
15
  "qairt": "2.50.0.260828221209"
16
  },
17
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet34_ssd1200/releases/v0.63.0/resnet34_ssd1200-qnn_dlc-float.zip"
18
  },
19
  "tflite": {
20
  "tool_versions": {
21
  "qairt": "2.50.0.260828221209"
22
  },
23
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet34_ssd1200/releases/v0.63.0/resnet34_ssd1200-tflite-float.zip"
24
  }
25
  }
26
  }
 
1
  {
2
+ "version": "0.64.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
6
  "onnx": {
7
  "tool_versions": {
8
  "qairt": "2.50.0.260828221209",
9
+ "onnx_runtime": "1.30.0"
10
  },
11
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet34_ssd1200/releases/v0.64.0/resnet34_ssd1200-onnx-float.zip"
12
  },
13
  "qnn_dlc": {
14
  "tool_versions": {
15
  "qairt": "2.50.0.260828221209"
16
  },
17
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet34_ssd1200/releases/v0.64.0/resnet34_ssd1200-qnn_dlc-float.zip"
18
  },
19
  "tflite": {
20
  "tool_versions": {
21
  "qairt": "2.50.0.260828221209"
22
  },
23
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet34_ssd1200/releases/v0.64.0/resnet34_ssd1200-tflite-float.zip"
24
  }
25
  }
26
  }