qaihm-bot commited on
Commit
e8a3507
·
verified ·
1 Parent(s): 08f98ab

See https://github.com/qualcomm/ai-hub-models/releases/v0.55.0 for changelog.

Files changed (2) hide show
  1. README.md +62 -47
  2. release_assets.json +6 -6
README.md CHANGED
@@ -29,10 +29,10 @@ Below are pre-exported model assets ready for deployment.
29
 
30
  | Runtime | Precision | Chipset | SDK Versions | Download |
31
  |---|---|---|---|---|
32
- | 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/efficientnet_b4/releases/v0.53.1/efficientnet_b4-onnx-float.zip)
33
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_b4/releases/v0.53.1/efficientnet_b4-qnn_dlc-float.zip)
34
- | QNN_DLC | w8a16 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_b4/releases/v0.53.1/efficientnet_b4-qnn_dlc-w8a16.zip)
35
- | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_b4/releases/v0.53.1/efficientnet_b4-tflite-float.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[EfficientNet-B4 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/efficientnet_b4)**.
38
 
@@ -62,49 +62,64 @@ See our repository for [EfficientNet-B4 on GitHub](https://github.com/qualcomm/a
62
  ## Performance Summary
63
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
64
  |---|---|---|---|---|---|---
65
- | EfficientNet-B4 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.467 ms | 1 - 78 MB | NPU
66
- | EfficientNet-B4 | ONNX | float | Snapdragon® 8 Elite Mobile | 1.759 ms | 0 - 71 MB | NPU
67
- | EfficientNet-B4 | ONNX | float | Snapdragon® X2 Elite | 1.628 ms | 45 - 45 MB | NPU
68
- | EfficientNet-B4 | ONNX | float | Snapdragon® X Elite | 3.346 ms | 45 - 45 MB | NPU
69
- | EfficientNet-B4 | ONNX | float | Snapdragon® X Elite | 3.346 ms | 45 - 45 MB | NPU
70
- | EfficientNet-B4 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 2.271 ms | 0 - 129 MB | NPU
71
- | EfficientNet-B4 | ONNX | float | Qualcomm® QCS8550 (Proxy) | 3.055 ms | 0 - 51 MB | NPU
72
- | EfficientNet-B4 | ONNX | float | Qualcomm® QCS9075 | 4.023 ms | 0 - 4 MB | NPU
73
- | EfficientNet-B4 | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.759 ms | 0 - 71 MB | NPU
74
- | EfficientNet-B4 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.507 ms | 0 - 68 MB | NPU
75
- | EfficientNet-B4 | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 1.842 ms | 0 - 69 MB | NPU
76
- | EfficientNet-B4 | QNN_DLC | float | Snapdragon® X2 Elite | 1.941 ms | 1 - 1 MB | NPU
77
- | EfficientNet-B4 | QNN_DLC | float | Snapdragon® X Elite | 3.599 ms | 1 - 1 MB | NPU
78
- | EfficientNet-B4 | QNN_DLC | float | Snapdragon® X Elite | 3.599 ms | 1 - 1 MB | NPU
79
- | EfficientNet-B4 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 2.385 ms | 0 - 117 MB | NPU
80
- | EfficientNet-B4 | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 12.006 ms | 1 - 65 MB | NPU
81
- | EfficientNet-B4 | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 3.347 ms | 0 - 30 MB | NPU
82
- | EfficientNet-B4 | QNN_DLC | float | Qualcomm® QCS9075 | 4.132 ms | 1 - 3 MB | NPU
83
- | EfficientNet-B4 | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 7.865 ms | 0 - 136 MB | NPU
84
- | EfficientNet-B4 | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.842 ms | 0 - 69 MB | NPU
85
- | EfficientNet-B4 | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 1.317 ms | 0 - 109 MB | NPU
86
- | EfficientNet-B4 | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 1.595 ms | 0 - 104 MB | NPU
87
- | EfficientNet-B4 | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 1.701 ms | 0 - 0 MB | NPU
88
- | EfficientNet-B4 | QNN_DLC | w8a16 | Snapdragon® X Elite | 3.763 ms | 0 - 0 MB | NPU
89
- | EfficientNet-B4 | QNN_DLC | w8a16 | Snapdragon® X Elite | 3.763 ms | 0 - 0 MB | NPU
90
- | EfficientNet-B4 | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 2.292 ms | 0 - 147 MB | NPU
91
- | EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® QCS6490 | 8.757 ms | 2 - 4 MB | NPU
92
- | EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 6.565 ms | 0 - 101 MB | NPU
93
- | EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 3.447 ms | 0 - 2 MB | NPU
94
- | EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 3.78 ms | 0 - 2 MB | NPU
95
- | EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 16.121 ms | 0 - 232 MB | NPU
96
- | EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® QCS8450 (Proxy) | 4.191 ms | 0 - 151 MB | NPU
97
- | EfficientNet-B4 | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 1.595 ms | 0 - 104 MB | NPU
98
- | EfficientNet-B4 | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 3.565 ms | 0 - 107 MB | NPU
99
- | EfficientNet-B4 | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 3.565 ms | 0 - 107 MB | NPU
100
- | EfficientNet-B4 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.509 ms | 0 - 85 MB | NPU
101
- | EfficientNet-B4 | TFLITE | float | Snapdragon® 8 Elite Mobile | 1.842 ms | 0 - 87 MB | NPU
102
- | EfficientNet-B4 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 2.397 ms | 0 - 145 MB | NPU
103
- | EfficientNet-B4 | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 12.043 ms | 0 - 82 MB | NPU
104
- | EfficientNet-B4 | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 3.307 ms | 0 - 2 MB | NPU
105
- | EfficientNet-B4 | TFLITE | float | Qualcomm® QCS9075 | 4.157 ms | 0 - 48 MB | NPU
106
- | EfficientNet-B4 | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 7.877 ms | 0 - 162 MB | NPU
107
- | EfficientNet-B4 | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.842 ms | 0 - 87 MB | NPU
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
108
 
109
  ## License
110
  * The license for the original implementation of EfficientNet-B4 can be found
 
29
 
30
  | Runtime | Precision | Chipset | SDK Versions | Download |
31
  |---|---|---|---|---|
32
+ | ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_b4/releases/v0.55.0/efficientnet_b4-onnx-float.zip)
33
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_b4/releases/v0.55.0/efficientnet_b4-qnn_dlc-float.zip)
34
+ | QNN_DLC | w8a16 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_b4/releases/v0.55.0/efficientnet_b4-qnn_dlc-w8a16.zip)
35
+ | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_b4/releases/v0.55.0/efficientnet_b4-tflite-float.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[EfficientNet-B4 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/efficientnet_b4)**.
38
 
 
62
  ## Performance Summary
63
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
64
  |---|---|---|---|---|---|---
65
+ | EfficientNet-B4 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.01 ms | 1 - 209 MB | NPU
66
+ | EfficientNet-B4 | ONNX | float | Snapdragon® X2 Elite | 3.926 ms | 210 - 210 MB | NPU
67
+ | EfficientNet-B4 | ONNX | float | Snapdragon® X Elite | 7.733 ms | 147 - 147 MB | NPU
68
+ | EfficientNet-B4 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.346 ms | 25 - 180 MB | NPU
69
+ | EfficientNet-B4 | ONNX | float | Qualcomm® QCS8550 (Proxy) | 7.374 ms | 2 - 95 MB | NPU
70
+ | EfficientNet-B4 | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.065 ms | 0 - 93 MB | NPU
71
+ | EfficientNet-B4 | ONNX | float | Qualcomm® QCS9075 | 10.766 ms | 2 - 47 MB | NPU
72
+ | EfficientNet-B4 | ONNX | float | Qualcomm® QCS8750 | 4.065 ms | 0 - 93 MB | NPU
73
+ | EfficientNet-B4 | ONNX | float | Qualcomm® QCS7181 | 7.733 ms | 147 - 147 MB | NPU
74
+ | EfficientNet-B4 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.243 ms | 2 - 205 MB | NPU
75
+ | EfficientNet-B4 | QNN_DLC | float | Snapdragon® X2 Elite | 4.507 ms | 2 - 2 MB | NPU
76
+ | EfficientNet-B4 | QNN_DLC | float | Snapdragon® X Elite | 8.904 ms | 2 - 2 MB | NPU
77
+ | EfficientNet-B4 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 5.813 ms | 0 - 142 MB | NPU
78
+ | EfficientNet-B4 | QNN_DLC | float | Qualcomm® QCS8275 | 29.139 ms | 2 - 81 MB | NPU
79
+ | EfficientNet-B4 | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 8.122 ms | 2 - 4 MB | NPU
80
+ | EfficientNet-B4 | QNN_DLC | float | Qualcomm® SA8775P | 10.306 ms | 2 - 85 MB | NPU
81
+ | EfficientNet-B4 | QNN_DLC | float | Qualcomm® SA8650P | 10.306 ms | 2 - 85 MB | NPU
82
+ | EfficientNet-B4 | QNN_DLC | float | Qualcomm® SA8255P | 10.306 ms | 2 - 85 MB | NPU
83
+ | EfficientNet-B4 | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 23.062 ms | 0 - 185 MB | NPU
84
+ | EfficientNet-B4 | QNN_DLC | float | Qualcomm® SA7255P | 29.139 ms | 2 - 81 MB | NPU
85
+ | EfficientNet-B4 | QNN_DLC | float | Qualcomm® SA8295P | 18.807 ms | 2 - 125 MB | NPU
86
+ | EfficientNet-B4 | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.308 ms | 0 - 85 MB | NPU
87
+ | EfficientNet-B4 | QNN_DLC | float | Qualcomm® QCS9075 | 12.186 ms | 2 - 5 MB | NPU
88
+ | EfficientNet-B4 | QNN_DLC | float | Qualcomm® QCS8750 | 4.308 ms | 0 - 85 MB | NPU
89
+ | EfficientNet-B4 | QNN_DLC | float | Qualcomm® QCS7181 | 8.904 ms | 2 - 2 MB | NPU
90
+ | EfficientNet-B4 | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.024 ms | 1 - 155 MB | NPU
91
+ | EfficientNet-B4 | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 3.547 ms | 1 - 1 MB | NPU
92
+ | EfficientNet-B4 | QNN_DLC | w8a16 | Snapdragon® X Elite | 9.056 ms | 1 - 1 MB | NPU
93
+ | EfficientNet-B4 | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 5.67 ms | 1 - 199 MB | NPU
94
+ | EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® QCS6490 | 22.892 ms | 3 - 5 MB | NPU
95
+ | EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® QCS8275 | 15.515 ms | 1 - 141 MB | NPU
96
+ | EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 8.38 ms | 1 - 3 MB | NPU
97
+ | EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® SA8775P | 8.934 ms | 1 - 144 MB | NPU
98
+ | EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® SA8650P | 8.934 ms | 1 - 144 MB | NPU
99
+ | EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® SA8255P | 8.934 ms | 1 - 144 MB | NPU
100
+ | EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 47.264 ms | 1 - 275 MB | NPU
101
+ | EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® SA7255P | 15.515 ms | 1 - 141 MB | NPU
102
+ | EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® SA8295P | 10.955 ms | 1 - 143 MB | NPU
103
+ | EfficientNet-B4 | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 9.702 ms | 1 - 269 MB | NPU
104
+ | EfficientNet-B4 | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 3.753 ms | 1 - 146 MB | NPU
105
+ | EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 9.888 ms | 0 - 3 MB | NPU
106
+ | EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® QCS8450 (Proxy) | 11.26 ms | 0 - 201 MB | NPU
107
+ | EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® QCS7790 | 9.702 ms | 1 - 269 MB | NPU
108
+ | EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® QCS8750 | 3.753 ms | 1 - 146 MB | NPU
109
+ | EfficientNet-B4 | QNN_DLC | w8a16 | Qualcomm® QCS7181 | 9.056 ms | 1 - 1 MB | NPU
110
+ | EfficientNet-B4 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.202 ms | 0 - 102 MB | NPU
111
+ | EfficientNet-B4 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.749 ms | 0 - 160 MB | NPU
112
+ | EfficientNet-B4 | TFLITE | float | Qualcomm® QCS8275 | 28.908 ms | 0 - 97 MB | NPU
113
+ | EfficientNet-B4 | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 8.032 ms | 0 - 2 MB | NPU
114
+ | EfficientNet-B4 | TFLITE | float | Qualcomm® SA8775P | 10.264 ms | 0 - 99 MB | NPU
115
+ | EfficientNet-B4 | TFLITE | float | Qualcomm® SA8650P | 10.264 ms | 0 - 99 MB | NPU
116
+ | EfficientNet-B4 | TFLITE | float | Qualcomm® SA8255P | 10.264 ms | 0 - 99 MB | NPU
117
+ | EfficientNet-B4 | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 21.932 ms | 0 - 202 MB | NPU
118
+ | EfficientNet-B4 | TFLITE | float | Qualcomm® SA7255P | 28.908 ms | 0 - 97 MB | NPU
119
+ | EfficientNet-B4 | TFLITE | float | Qualcomm® SA8295P | 18.861 ms | 0 - 140 MB | NPU
120
+ | EfficientNet-B4 | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.319 ms | 0 - 105 MB | NPU
121
+ | EfficientNet-B4 | TFLITE | float | Qualcomm® QCS9075 | 10.99 ms | 0 - 49 MB | NPU
122
+ | EfficientNet-B4 | TFLITE | float | Qualcomm® QCS8750 | 4.319 ms | 0 - 105 MB | NPU
123
 
124
  ## License
125
  * The license for the original implementation of EfficientNet-B4 can be found
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.53.1",
3
  "precisions": {
4
  "w8a16": {
5
  "universal_assets": {
@@ -7,7 +7,7 @@
7
  "tool_versions": {
8
  "qairt": "2.45.0.260326154327"
9
  },
10
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_b4/releases/v0.53.1/efficientnet_b4-qnn_dlc-w8a16.zip"
11
  }
12
  }
13
  },
@@ -18,20 +18,20 @@
18
  "qairt": "2.45.0.260326154327",
19
  "litert": "1.4.3"
20
  },
21
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_b4/releases/v0.53.1/efficientnet_b4-tflite-float.zip"
22
  },
23
  "qnn_dlc": {
24
  "tool_versions": {
25
  "qairt": "2.45.0.260326154327"
26
  },
27
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_b4/releases/v0.53.1/efficientnet_b4-qnn_dlc-float.zip"
28
  },
29
  "onnx": {
30
  "tool_versions": {
31
  "qairt": "2.42.0.251225135753_193295",
32
- "onnx_runtime": "1.24.3"
33
  },
34
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_b4/releases/v0.53.1/efficientnet_b4-onnx-float.zip"
35
  }
36
  }
37
  }
 
1
  {
2
+ "version": "0.55.0",
3
  "precisions": {
4
  "w8a16": {
5
  "universal_assets": {
 
7
  "tool_versions": {
8
  "qairt": "2.45.0.260326154327"
9
  },
10
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_b4/releases/v0.55.0/efficientnet_b4-qnn_dlc-w8a16.zip"
11
  }
12
  }
13
  },
 
18
  "qairt": "2.45.0.260326154327",
19
  "litert": "1.4.3"
20
  },
21
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_b4/releases/v0.55.0/efficientnet_b4-tflite-float.zip"
22
  },
23
  "qnn_dlc": {
24
  "tool_versions": {
25
  "qairt": "2.45.0.260326154327"
26
  },
27
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_b4/releases/v0.55.0/efficientnet_b4-qnn_dlc-float.zip"
28
  },
29
  "onnx": {
30
  "tool_versions": {
31
  "qairt": "2.42.0.251225135753_193295",
32
+ "onnx_runtime": "1.25.0"
33
  },
34
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_b4/releases/v0.55.0/efficientnet_b4-onnx-float.zip"
35
  }
36
  }
37
  }