qaihm-bot commited on
Commit
66a712d
·
verified ·
1 Parent(s): a1ffa95

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

Files changed (2) hide show
  1. README.md +40 -35
  2. release_assets.json +6 -6
README.md CHANGED
@@ -15,7 +15,7 @@ pipeline_tag: object-detection
15
  DETR is a machine learning model that can detect objects (trained on COCO dataset).
16
 
17
  This is based on the implementation of DETR-ResNet50 found [here](https://github.com/facebookresearch/detr).
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/v0.63.0/src/qai_hub_models/models/detr_resnet50) 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
 
@@ -28,25 +28,25 @@ Below are pre-exported model assets ready for deployment.
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
- | 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/detr_resnet50/releases/v0.63.0/detr_resnet50-onnx-float.zip)
32
- | ONNX | w8a16_mixed_fp16 | Universal | QAIRT 2.50, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/detr_resnet50/releases/v0.63.0/detr_resnet50-onnx-w8a16_mixed_fp16.zip)
33
- | QNN_DLC | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/detr_resnet50/releases/v0.63.0/detr_resnet50-qnn_dlc-float.zip)
34
- | QNN_DLC | w8a16_mixed_fp16 | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/detr_resnet50/releases/v0.63.0/detr_resnet50-qnn_dlc-w8a16_mixed_fp16.zip)
35
- | TFLITE | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/detr_resnet50/releases/v0.63.0/detr_resnet50-tflite-float.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[DETR-ResNet50 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/detr_resnet50)**.
38
 
39
 
40
  ### Option 2: Export with Custom Configurations
41
 
42
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/detr_resnet50) Python library to compile and export the model with your own:
43
  - Custom weights (e.g., fine-tuned checkpoints)
44
  - Custom input shapes
45
  - Target device and runtime configurations
46
 
47
  This option is ideal if you need to customize the model beyond the default configuration provided here.
48
 
49
- See our repository for [DETR-ResNet50 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/detr_resnet50) for usage instructions.
50
 
51
  ## Model Details
52
 
@@ -81,42 +81,47 @@ See our repository for [DETR-ResNet50 on GitHub](https://github.com/qualcomm/ai-
81
  | DETR-ResNet50 | ONNX | w8a16_mixed_fp16 | Qualcomm® QCS8450 | 97.068 ms | 7 - 466 MB | NPU
82
  | DETR-ResNet50 | ONNX | w8a16_mixed_fp16 | Qualcomm® Dragonwing™ IQ-9075 | 46.732 ms | 23 - 25 MB | NPU
83
  | DETR-ResNet50 | ONNX | w8a16_mixed_fp16 | Qualcomm® Dragonwing™ Q-8750 | 31.162 ms | 20 - 271 MB | NPU
84
- | DETR-ResNet50 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 7.92 ms | 5 - 278 MB | NPU
85
- | DETR-ResNet50 | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 10.313 ms | 5 - 264 MB | NPU
86
- | DETR-ResNet50 | QNN_DLC | float | Snapdragon® X2 Elite | 9.25 ms | 5 - 5 MB | NPU
87
- | DETR-ResNet50 | QNN_DLC | float | Snapdragon® X Elite | 19.24 ms | 5 - 5 MB | NPU
88
- | DETR-ResNet50 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 13.709 ms | 3 - 341 MB | NPU
89
- | DETR-ResNet50 | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 28.189 ms | 4 - 292 MB | NPU
90
- | DETR-ResNet50 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 27.309 ms | 5 - 12 MB | NPU
91
- | DETR-ResNet50 | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 18.874 ms | 5 - 7 MB | NPU
92
- | DETR-ResNet50 | QNN_DLC | float | Qualcomm® SA8650P | 26.853 ms | 1 - 300 MB | NPU
93
- | DETR-ResNet50 | QNN_DLC | float | Qualcomm® SA8255P | 26.853 ms | 1 - 300 MB | NPU
94
- | DETR-ResNet50 | QNN_DLC | float | Qualcomm® QCS8450 | 28.189 ms | 4 - 292 MB | NPU
95
- | DETR-ResNet50 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 27.22 ms | 7 - 14 MB | NPU
96
- | DETR-ResNet50 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 19.24 ms | 5 - 5 MB | NPU
97
- | DETR-ResNet50 | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 10.313 ms | 5 - 264 MB | NPU
98
- | DETR-ResNet50 | QNN_DLC | float | Qualcomm® SA8295P | 29.319 ms | 0 - 218 MB | NPU
99
- | DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 10.826 ms | 2 - 306 MB | NPU
100
- | DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Snapdragon® 8 Elite For Galaxy Mobile | 12.726 ms | 0 - 286 MB | NPU
101
- | DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Snapdragon® X2 Elite | 11.199 ms | 2 - 2 MB | NPU
102
- | DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Snapdragon® X Elite | 23.917 ms | 2 - 2 MB | NPU
103
- | DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Snapdragon® 8 Gen 3 Mobile | 17.728 ms | 2 - 370 MB | NPU
104
- | DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® Dragonwing™ IQ-8275 | 28.567 ms | 2 - 8 MB | NPU
105
- | DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 24.229 ms | 2 - 5 MB | NPU
106
- | DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® Dragonwing™ IQ-9075 | 28.548 ms | 2 - 6 MB | NPU
107
- | DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® Dragonwing™ IQ-X7181 | 23.917 ms | 2 - 2 MB | NPU
108
- | DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® Dragonwing™ Q-8750 | 12.726 ms | 0 - 286 MB | NPU
 
 
 
 
 
 
109
  | DETR-ResNet50 | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 7.948 ms | 0 - 301 MB | NPU
110
  | DETR-ResNet50 | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 10.35 ms | 0 - 290 MB | NPU
111
  | DETR-ResNet50 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 13.575 ms | 0 - 362 MB | NPU
112
  | DETR-ResNet50 | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 27.991 ms | 0 - 313 MB | NPU
113
  | DETR-ResNet50 | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 27.444 ms | 0 - 89 MB | NPU
114
  | DETR-ResNet50 | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 19.107 ms | 0 - 2 MB | NPU
115
- | DETR-ResNet50 | TFLITE | float | Qualcomm® SA8650P | 26.917 ms | 0 - 323 MB | NPU
116
- | DETR-ResNet50 | TFLITE | float | Qualcomm® SA8255P | 26.917 ms | 0 - 323 MB | NPU
117
  | DETR-ResNet50 | TFLITE | float | Qualcomm® QCS8450 | 27.991 ms | 0 - 313 MB | NPU
118
  | DETR-ResNet50 | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 26.677 ms | 0 - 89 MB | NPU
119
  | DETR-ResNet50 | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 10.35 ms | 0 - 290 MB | NPU
 
120
  | DETR-ResNet50 | TFLITE | float | Qualcomm® SA8295P | 29.311 ms | 0 - 237 MB | NPU
121
 
122
  ## License
 
15
  DETR is a machine learning model that can detect objects (trained on COCO dataset).
16
 
17
  This is based on the implementation of DETR-ResNet50 found [here](https://github.com/facebookresearch/detr).
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/v0.64.0/src/qai_hub_models/models/detr_resnet50) 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 | 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/detr_resnet50/releases/v0.64.0/detr_resnet50-onnx-float.zip)
32
+ | ONNX | w8a16_mixed_fp16 | Universal | QAIRT 2.50, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/detr_resnet50/releases/v0.64.0/detr_resnet50-onnx-w8a16_mixed_fp16.zip)
33
+ | QNN_DLC | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/detr_resnet50/releases/v0.64.0/detr_resnet50-qnn_dlc-float.zip)
34
+ | QNN_DLC | w8a16_mixed_fp16 | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/detr_resnet50/releases/v0.64.0/detr_resnet50-qnn_dlc-w8a16_mixed_fp16.zip)
35
+ | TFLITE | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/detr_resnet50/releases/v0.64.0/detr_resnet50-tflite-float.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[DETR-ResNet50 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/detr_resnet50)**.
38
 
39
 
40
  ### Option 2: Export with Custom Configurations
41
 
42
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.64.0/src/qai_hub_models/models/detr_resnet50) Python library to compile and export the model with your own:
43
  - Custom weights (e.g., fine-tuned checkpoints)
44
  - Custom input shapes
45
  - Target device and runtime configurations
46
 
47
  This option is ideal if you need to customize the model beyond the default configuration provided here.
48
 
49
+ See our repository for [DETR-ResNet50 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.64.0/src/qai_hub_models/models/detr_resnet50) for usage instructions.
50
 
51
  ## Model Details
52
 
 
81
  | DETR-ResNet50 | ONNX | w8a16_mixed_fp16 | Qualcomm® QCS8450 | 97.068 ms | 7 - 466 MB | NPU
82
  | DETR-ResNet50 | ONNX | w8a16_mixed_fp16 | Qualcomm® Dragonwing™ IQ-9075 | 46.732 ms | 23 - 25 MB | NPU
83
  | DETR-ResNet50 | ONNX | w8a16_mixed_fp16 | Qualcomm® Dragonwing™ Q-8750 | 31.162 ms | 20 - 271 MB | NPU
84
+ | DETR-ResNet50 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 7.938 ms | 5 - 278 MB | NPU
85
+ | DETR-ResNet50 | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 10.344 ms | 3 - 266 MB | NPU
86
+ | DETR-ResNet50 | QNN_DLC | float | Snapdragon® X2 Elite | 8.847 ms | 5 - 5 MB | NPU
87
+ | DETR-ResNet50 | QNN_DLC | float | Snapdragon® X Elite | 19.33 ms | 5 - 5 MB | NPU
88
+ | DETR-ResNet50 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 13.581 ms | 5 - 342 MB | NPU
89
+ | DETR-ResNet50 | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 28.19 ms | 2 - 292 MB | NPU
90
+ | DETR-ResNet50 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 27.391 ms | 5 - 12 MB | NPU
91
+ | DETR-ResNet50 | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 18.88 ms | 5 - 7 MB | NPU
92
+ | DETR-ResNet50 | QNN_DLC | float | Qualcomm® SA8775P | 26.419 ms | 1 - 254 MB | NPU
93
+ | DETR-ResNet50 | QNN_DLC | float | Qualcomm® SA8650P | 26.419 ms | 1 - 254 MB | NPU
94
+ | DETR-ResNet50 | QNN_DLC | float | Qualcomm® SA8255P | 26.419 ms | 1 - 254 MB | NPU
95
+ | DETR-ResNet50 | QNN_DLC | float | Qualcomm® QCS8450 | 28.19 ms | 2 - 292 MB | NPU
96
+ | DETR-ResNet50 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 26.702 ms | 5 - 12 MB | NPU
97
+ | DETR-ResNet50 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 19.33 ms | 5 - 5 MB | NPU
98
+ | DETR-ResNet50 | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 10.344 ms | 3 - 266 MB | NPU
99
+ | DETR-ResNet50 | QNN_DLC | float | Qualcomm® SA7255P | 85.247 ms | 1 - 254 MB | NPU
100
+ | DETR-ResNet50 | QNN_DLC | float | Qualcomm® SA8295P | 29.316 ms | 0 - 218 MB | NPU
101
+ | DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 10.833 ms | 2 - 305 MB | NPU
102
+ | DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Snapdragon® 8 Elite For Galaxy Mobile | 12.493 ms | 0 - 286 MB | NPU
103
+ | DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Snapdragon® X2 Elite | 13.363 ms | 2 - 2 MB | NPU
104
+ | DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Snapdragon® X Elite | 23.9 ms | 2 - 2 MB | NPU
105
+ | DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Snapdragon® 8 Gen 3 Mobile | 17.762 ms | 2 - 371 MB | NPU
106
+ | DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® Dragonwing™ IQ-8275 | 28.672 ms | 2 - 8 MB | NPU
107
+ | DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 24.205 ms | 2 - 5 MB | NPU
108
+ | DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® SA8775P | 28.204 ms | 1 - 280 MB | NPU
109
+ | DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® SA8650P | 28.204 ms | 1 - 280 MB | NPU
110
+ | DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® SA8255P | 28.204 ms | 1 - 280 MB | NPU
111
+ | DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® Dragonwing™ IQ-9075 | 28.781 ms | 4 - 9 MB | NPU
112
+ | DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® Dragonwing™ IQ-X7181 | 23.9 ms | 2 - 2 MB | NPU
113
+ | DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® Dragonwing™ Q-8750 | 12.493 ms | 0 - 286 MB | NPU
114
+ | DETR-ResNet50 | QNN_DLC | w8a16_mixed_fp16 | Qualcomm® SA7255P | 73.556 ms | 1 - 279 MB | NPU
115
  | DETR-ResNet50 | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 7.948 ms | 0 - 301 MB | NPU
116
  | DETR-ResNet50 | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 10.35 ms | 0 - 290 MB | NPU
117
  | DETR-ResNet50 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 13.575 ms | 0 - 362 MB | NPU
118
  | DETR-ResNet50 | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 27.991 ms | 0 - 313 MB | NPU
119
  | DETR-ResNet50 | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 27.444 ms | 0 - 89 MB | NPU
120
  | DETR-ResNet50 | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 19.107 ms | 0 - 2 MB | NPU
 
 
121
  | DETR-ResNet50 | TFLITE | float | Qualcomm® QCS8450 | 27.991 ms | 0 - 313 MB | NPU
122
  | DETR-ResNet50 | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 26.677 ms | 0 - 89 MB | NPU
123
  | DETR-ResNet50 | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 10.35 ms | 0 - 290 MB | NPU
124
+ | DETR-ResNet50 | TFLITE | float | Qualcomm® SA7255P | 85.243 ms | 0 - 278 MB | NPU
125
  | DETR-ResNet50 | TFLITE | float | Qualcomm® SA8295P | 29.311 ms | 0 - 237 MB | NPU
126
 
127
  ## License
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.63.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
@@ -8,19 +8,19 @@
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/detr_resnet50/releases/v0.63.0/detr_resnet50-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/detr_resnet50/releases/v0.63.0/detr_resnet50-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/detr_resnet50/releases/v0.63.0/detr_resnet50-tflite-float.zip"
24
  }
25
  }
26
  },
@@ -31,13 +31,13 @@
31
  "qairt": "2.50.0.260828221209",
32
  "onnx_runtime": "1.27.1"
33
  },
34
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/detr_resnet50/releases/v0.63.0/detr_resnet50-onnx-w8a16_mixed_fp16.zip"
35
  },
36
  "qnn_dlc": {
37
  "tool_versions": {
38
  "qairt": "2.50.0.260828221209"
39
  },
40
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/detr_resnet50/releases/v0.63.0/detr_resnet50-qnn_dlc-w8a16_mixed_fp16.zip"
41
  }
42
  }
43
  }
 
1
  {
2
+ "version": "0.64.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
 
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/detr_resnet50/releases/v0.64.0/detr_resnet50-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/detr_resnet50/releases/v0.64.0/detr_resnet50-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/detr_resnet50/releases/v0.64.0/detr_resnet50-tflite-float.zip"
24
  }
25
  }
26
  },
 
31
  "qairt": "2.50.0.260828221209",
32
  "onnx_runtime": "1.27.1"
33
  },
34
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/detr_resnet50/releases/v0.64.0/detr_resnet50-onnx-w8a16_mixed_fp16.zip"
35
  },
36
  "qnn_dlc": {
37
  "tool_versions": {
38
  "qairt": "2.50.0.260828221209"
39
  },
40
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/detr_resnet50/releases/v0.64.0/detr_resnet50-qnn_dlc-w8a16_mixed_fp16.zip"
41
  }
42
  }
43
  }