Hugging Face's logo

qualcomm
/
ResNet34-SSD

Object Detection
PyTorch
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
e58fd1c
·
verified ·
1 Parent(s): c98b9d9

v0.60.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.60.0 for changelog.

Files changed (2) hide show
  1. README.md +53 -50
  2. release_assets.json +4 -4
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/v0.59.0/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
 
@@ -27,79 +27,82 @@ Below are pre-exported model assets ready for deployment.
27
 
28
  | Runtime | Precision | Chipset | SDK Versions | Download |
29
  |---|---|---|---|---|
30
- | ONNX | float | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet34_ssd1200/releases/v0.59.0/resnet34_ssd1200-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/resnet34_ssd1200/releases/v0.59.0/resnet34_ssd1200-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/resnet34_ssd1200/releases/v0.59.0/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/v0.59.0/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/v0.59.0/src/qai_hub_models/models/resnet34_ssd1200) for usage instructions.
47
 
48
  ## Model Details
49
 
50
  **Model Type:** Model_use_case.object_detection
51
 
52
  **Model Stats:**
53
- - Model checkpoint: resnet34-ssd1200
54
  - Input resolution: 1x3x1200x1200
55
- - Number of parameters: 20.0M
56
  - Model size (float): 76.2 MB
 
57
 
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® X2 Elite | 43.332 ms | 17 - 17 MB | NPU
62
- | ResNet34-SSD | ONNX | float | Snapdragon® X Elite | 88.328 ms | 30 - 30 MB | NPU
63
- | ResNet34-SSD | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 63.01 ms | 3 - 501 MB | NPU
64
- | ResNet34-SSD | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 179.687 ms | 17 - 445 MB | NPU
65
- | ResNet34-SSD | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 87.363 ms | 0 - 31 MB | NPU
66
- | ResNet34-SSD | ONNX | float | Qualcomm® QCS8450 | 179.687 ms | 17 - 445 MB | NPU
67
- | ResNet34-SSD | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 133.727 ms | 16 - 36 MB | NPU
68
- | ResNet34-SSD | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 88.328 ms | 30 - 30 MB | NPU
69
- | ResNet34-SSD | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 52.078 ms | 1 - 423 MB | NPU
70
- | ResNet34-SSD | ONNX | float | Snapdragon® 8 Elite Mobile | 52.078 ms | 1 - 423 MB | NPU
71
- | ResNet34-SSD | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 38.973 ms | 0 - 489 MB | NPU
72
- | ResNet34-SSD | QNN_DLC | float | Snapdragon® X2 Elite | 61.973 ms | 17 - 17 MB | NPU
73
- | ResNet34-SSD | QNN_DLC | float | Snapdragon® X Elite | 130.901 ms | 17 - 17 MB | NPU
74
- | ResNet34-SSD | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 84.929 ms | 15 - 604 MB | NPU
75
- | ResNet34-SSD | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 261.455 ms | 3 - 509 MB | NPU
76
- | ResNet34-SSD | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8275 | 481.745 ms | 16 - 384 MB | NPU
77
- | ResNet34-SSD | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 129.444 ms | 17 - 19 MB | NPU
78
- | ResNet34-SSD | QNN_DLC | float | Qualcomm® SA8775P | 173.627 ms | 16 - 385 MB | NPU
79
- | ResNet34-SSD | QNN_DLC | float | Qualcomm® SA8650P | 173.627 ms | 16 - 385 MB | NPU
80
- | ResNet34-SSD | QNN_DLC | float | Qualcomm® SA8255P | 173.627 ms | 16 - 385 MB | NPU
81
- | ResNet34-SSD | QNN_DLC | float | Qualcomm® QCS8450 | 261.455 ms | 3 - 509 MB | NPU
82
- | ResNet34-SSD | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 172.622 ms | 18 - 37 MB | NPU
83
- | ResNet34-SSD | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 130.901 ms | 17 - 17 MB | NPU
84
- | ResNet34-SSD | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 67.015 ms | 16 - 391 MB | NPU
85
- | ResNet34-SSD | QNN_DLC | float | Qualcomm® SA7255P | 481.745 ms | 16 - 384 MB | NPU
86
- | ResNet34-SSD | QNN_DLC | float | Qualcomm® SA8295P | 183.702 ms | 0 - 329 MB | NPU
87
- | ResNet34-SSD | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 67.015 ms | 16 - 391 MB | NPU
88
- | ResNet34-SSD | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 52.389 ms | 8 - 547 MB | NPU
89
- | ResNet34-SSD | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 107.47 ms | 0 - 542 MB | NPU
90
- | ResNet34-SSD | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 233.539 ms | 1 - 621 MB | NPU
91
- | ResNet34-SSD | TFLITE | float | Qualcomm® Dragonwing™ QCS8275 | 513.176 ms | 0 - 378 MB | NPU
92
- | ResNet34-SSD | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 146.676 ms | 0 - 3 MB | NPU
93
- | ResNet34-SSD | TFLITE | float | Qualcomm® SA8775P | 183.849 ms | 1 - 427 MB | NPU
94
- | ResNet34-SSD | TFLITE | float | Qualcomm® SA8650P | 183.849 ms | 1 - 427 MB | NPU
95
- | ResNet34-SSD | TFLITE | float | Qualcomm® SA8255P | 183.849 ms | 1 - 427 MB | NPU
96
- | ResNet34-SSD | TFLITE | float | Qualcomm® QCS8450 | 233.539 ms | 1 - 621 MB | NPU
97
- | ResNet34-SSD | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 181.406 ms | 0 - 65 MB | NPU
98
- | ResNet34-SSD | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 87.816 ms | 0 - 403 MB | NPU
99
- | ResNet34-SSD | TFLITE | float | Qualcomm® SA7255P | 513.176 ms | 0 - 378 MB | NPU
100
- | ResNet34-SSD | TFLITE | float | Qualcomm® SA8295P | 202.221 ms | 0 - 353 MB | NPU
101
- | ResNet34-SSD | TFLITE | float | Snapdragon® 8 Elite Mobile | 87.816 ms | 0 - 403 MB | NPU
102
- | ResNet34-SSD | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 72.472 ms | 0 - 570 MB | NPU
 
 
 
103
 
104
  ## License
105
  * 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/v0.60.0/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 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet34_ssd1200/releases/v0.60.0/resnet34_ssd1200-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/resnet34_ssd1200/releases/v0.60.0/resnet34_ssd1200-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/resnet34_ssd1200/releases/v0.60.0/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/v0.60.0/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/v0.60.0/src/qai_hub_models/models/resnet34_ssd1200) for usage instructions.
47
 
48
  ## Model Details
49
 
50
  **Model Type:** Model_use_case.object_detection
51
 
52
  **Model Stats:**
 
53
  - Input resolution: 1x3x1200x1200
54
+ - Model checkpoint: resnet34-ssd1200
55
  - Model size (float): 76.2 MB
56
+ - Number of parameters: 20.0M
57
 
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® X2 Elite | 43.227 ms | 17 - 17 MB | NPU
62
+ | ResNet34-SSD | ONNX | float | Snapdragon® X Elite | 88.356 ms | 30 - 30 MB | NPU
63
+ | ResNet34-SSD | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 63.393 ms | 17 - 518 MB | NPU
64
+ | ResNet34-SSD | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 176.166 ms | 1 - 428 MB | NPU
65
+ | ResNet34-SSD | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 142.042 ms | 16 - 36 MB | NPU
66
+ | ResNet34-SSD | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 87.968 ms | 0 - 36 MB | NPU
67
+ | ResNet34-SSD | ONNX | float | Qualcomm® QCS8450 | 176.166 ms | 1 - 428 MB | NPU
68
+ | ResNet34-SSD | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 143.91 ms | 16 - 36 MB | NPU
69
+ | ResNet34-SSD | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 88.356 ms | 30 - 30 MB | NPU
70
+ | ResNet34-SSD | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 52.011 ms | 1 - 424 MB | NPU
71
+ | ResNet34-SSD | ONNX | float | Snapdragon® 8 Elite Mobile | 52.011 ms | 1 - 424 MB | NPU
72
+ | ResNet34-SSD | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 38.954 ms | 0 - 492 MB | NPU
73
+ | ResNet34-SSD | QNN_DLC | float | Snapdragon® X2 Elite | 62.034 ms | 17 - 17 MB | NPU
74
+ | ResNet34-SSD | QNN_DLC | float | Snapdragon® X Elite | 129.612 ms | 17 - 17 MB | NPU
75
+ | ResNet34-SSD | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 85.001 ms | 16 - 604 MB | NPU
76
+ | ResNet34-SSD | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 260.874 ms | 3 - 509 MB | NPU
77
+ | ResNet34-SSD | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 168.201 ms | 17 - 35 MB | NPU
78
+ | ResNet34-SSD | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 482.663 ms | 16 - 384 MB | NPU
79
+ | ResNet34-SSD | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 129.04 ms | 17 - 18 MB | NPU
80
+ | ResNet34-SSD | QNN_DLC | float | Qualcomm® SA8775P | 173.767 ms | 16 - 385 MB | NPU
81
+ | ResNet34-SSD | QNN_DLC | float | Qualcomm® SA8650P | 173.767 ms | 16 - 385 MB | NPU
82
+ | ResNet34-SSD | QNN_DLC | float | Qualcomm® SA8255P | 173.767 ms | 16 - 385 MB | NPU
83
+ | ResNet34-SSD | QNN_DLC | float | Qualcomm® QCS8450 | 260.874 ms | 3 - 509 MB | NPU
84
+ | ResNet34-SSD | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 172.761 ms | 17 - 35 MB | NPU
85
+ | ResNet34-SSD | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 129.612 ms | 17 - 17 MB | NPU
86
+ | ResNet34-SSD | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 67.171 ms | 12 - 388 MB | NPU
87
+ | ResNet34-SSD | QNN_DLC | float | Qualcomm® SA7255P | 482.663 ms | 16 - 384 MB | NPU
88
+ | ResNet34-SSD | QNN_DLC | float | Qualcomm® SA8295P | 183.467 ms | 0 - 329 MB | NPU
89
+ | ResNet34-SSD | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 67.171 ms | 12 - 388 MB | NPU
90
+ | ResNet34-SSD | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 52.284 ms | 12 - 559 MB | NPU
91
+ | ResNet34-SSD | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 107.67 ms | 0 - 543 MB | NPU
92
+ | ResNet34-SSD | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 236.469 ms | 0 - 619 MB | NPU
93
+ | ResNet34-SSD | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 187.29 ms | 0 - 66 MB | NPU
94
+ | ResNet34-SSD | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 513.165 ms | 0 - 378 MB | NPU
95
+ | ResNet34-SSD | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 145.953 ms | 0 - 4 MB | NPU
96
+ | ResNet34-SSD | TFLITE | float | Qualcomm® SA8775P | 183.807 ms | 0 - 426 MB | NPU
97
+ | ResNet34-SSD | TFLITE | float | Qualcomm® SA8650P | 183.807 ms | 0 - 426 MB | NPU
98
+ | ResNet34-SSD | TFLITE | float | Qualcomm® SA8255P | 183.807 ms | 0 - 426 MB | NPU
99
+ | ResNet34-SSD | TFLITE | float | Qualcomm® QCS8450 | 236.469 ms | 0 - 619 MB | NPU
100
+ | ResNet34-SSD | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 180.674 ms | 0 - 65 MB | NPU
101
+ | ResNet34-SSD | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 87.444 ms | 0 - 402 MB | NPU
102
+ | ResNet34-SSD | TFLITE | float | Qualcomm® SA7255P | 513.165 ms | 0 - 378 MB | NPU
103
+ | ResNet34-SSD | TFLITE | float | Qualcomm® SA8295P | 202.27 ms | 0 - 354 MB | NPU
104
+ | ResNet34-SSD | TFLITE | float | Snapdragon® 8 Elite Mobile | 87.444 ms | 0 - 402 MB | NPU
105
+ | ResNet34-SSD | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 72.293 ms | 0 - 569 MB | NPU
106
 
107
  ## License
108
  * The license for the original implementation of ResNet34-SSD can be found
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.59.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
@@ -8,19 +8,19 @@
8
  "qairt": "2.45.0.260326154327",
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/v0.59.0/resnet34_ssd1200-onnx-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/resnet34_ssd1200/releases/v0.59.0/resnet34_ssd1200-qnn_dlc-float.zip"
18
  },
19
  "tflite": {
20
  "tool_versions": {
21
  "qairt": "2.45.0.260326154327"
22
  },
23
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet34_ssd1200/releases/v0.59.0/resnet34_ssd1200-tflite-float.zip"
24
  }
25
  }
26
  }
 
1
  {
2
+ "version": "0.60.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
 
8
  "qairt": "2.45.0.260326154327",
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/v0.60.0/resnet34_ssd1200-onnx-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/resnet34_ssd1200/releases/v0.60.0/resnet34_ssd1200-qnn_dlc-float.zip"
18
  },
19
  "tflite": {
20
  "tool_versions": {
21
  "qairt": "2.45.0.260326154327"
22
  },
23
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet34_ssd1200/releases/v0.60.0/resnet34_ssd1200-tflite-float.zip"
24
  }
25
  }
26
  }