qaihm-bot commited on
Commit
2d6c0b1
·
verified ·
1 Parent(s): 1b7f1c2

See https://github.com/quic/ai-hub-models/releases/v0.47.0 for changelog.

Files changed (1) hide show
  1. README.md +47 -43
README.md CHANGED
@@ -28,11 +28,11 @@ Below are pre-exported model assets ready for deployment.
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
- | ONNX | float | Universal | QAIRT 2.37, ONNX Runtime 1.23.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientformer/releases/v0.46.0/efficientformer-onnx-float.zip)
32
- | ONNX | w8a16 | Universal | QAIRT 2.37, ONNX Runtime 1.23.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientformer/releases/v0.46.0/efficientformer-onnx-w8a16.zip)
33
- | QNN_DLC | float | Universal | QAIRT 2.42 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientformer/releases/v0.46.0/efficientformer-qnn_dlc-float.zip)
34
- | QNN_DLC | w8a16 | Universal | QAIRT 2.42 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientformer/releases/v0.46.0/efficientformer-qnn_dlc-w8a16.zip)
35
- | TFLITE | float | Universal | QAIRT 2.42, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientformer/releases/v0.46.0/efficientformer-tflite-float.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[EfficientFormer on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/efficientformer)**.
38
 
@@ -62,45 +62,49 @@ See our repository for [EfficientFormer on GitHub](https://github.com/quic/ai-hu
62
  ## Performance Summary
63
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
64
  |---|---|---|---|---|---|---
65
- | EfficientFormer | ONNX | float | Snapdragon® X Elite | 1.634 ms | 24 - 24 MB | NPU
66
- | EfficientFormer | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.166 ms | 0 - 148 MB | NPU
67
- | EfficientFormer | ONNX | float | Qualcomm® QCS8550 (Proxy) | 1.713 ms | 0 - 63 MB | NPU
68
- | EfficientFormer | ONNX | float | Qualcomm® QCS9075 | 2.101 ms | 1 - 3 MB | NPU
69
- | EfficientFormer | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.963 ms | 0 - 114 MB | NPU
70
- | EfficientFormer | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.869 ms | 0 - 113 MB | NPU
71
- | EfficientFormer | ONNX | w8a16 | Snapdragon® X Elite | 6.347 ms | 10 - 10 MB | NPU
72
- | EfficientFormer | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 5.97 ms | 5 - 151 MB | NPU
73
- | EfficientFormer | ONNX | w8a16 | Qualcomm® QCS6490 | 144.626 ms | 19 - 25 MB | CPU
74
- | EfficientFormer | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 7.312 ms | 5 - 11 MB | NPU
75
- | EfficientFormer | ONNX | w8a16 | Qualcomm® QCS9075 | 9.286 ms | 5 - 8 MB | NPU
76
- | EfficientFormer | ONNX | w8a16 | Qualcomm® QCM6690 | 63.675 ms | 22 - 30 MB | CPU
77
- | EfficientFormer | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 5.362 ms | 5 - 123 MB | NPU
78
- | EfficientFormer | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 60.202 ms | 21 - 30 MB | CPU
79
- | EfficientFormer | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 4.916 ms | 0 - 121 MB | NPU
80
- | EfficientFormer | QNN_DLC | float | Snapdragon® X Elite | 1.728 ms | 1 - 1 MB | NPU
81
- | EfficientFormer | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.038 ms | 0 - 80 MB | NPU
82
- | EfficientFormer | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 4.975 ms | 1 - 46 MB | NPU
83
- | EfficientFormer | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 1.553 ms | 1 - 3 MB | NPU
84
- | EfficientFormer | QNN_DLC | float | Qualcomm® QCS9075 | 1.999 ms | 3 - 5 MB | NPU
85
- | EfficientFormer | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 5.62 ms | 0 - 82 MB | NPU
86
- | EfficientFormer | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.79 ms | 0 - 48 MB | NPU
 
 
87
  | EfficientFormer | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.649 ms | 1 - 49 MB | NPU
88
- | EfficientFormer | QNN_DLC | w8a16 | Snapdragon® X Elite | 1.845 ms | 0 - 0 MB | NPU
89
- | EfficientFormer | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1.084 ms | 0 - 78 MB | NPU
90
- | EfficientFormer | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 3.253 ms | 0 - 57 MB | NPU
91
- | EfficientFormer | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 1.604 ms | 0 - 2 MB | NPU
92
- | EfficientFormer | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 1.775 ms | 2 - 4 MB | NPU
93
- | EfficientFormer | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 7.064 ms | 0 - 177 MB | NPU
94
- | EfficientFormer | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 0.711 ms | 0 - 49 MB | NPU
95
- | EfficientFormer | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 1.701 ms | 0 - 60 MB | NPU
96
- | EfficientFormer | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.579 ms | 0 - 58 MB | NPU
97
- | EfficientFormer | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.035 ms | 0 - 104 MB | NPU
98
- | EfficientFormer | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 4.928 ms | 0 - 66 MB | NPU
99
- | EfficientFormer | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 1.47 ms | 0 - 3 MB | NPU
100
- | EfficientFormer | TFLITE | float | Qualcomm® QCS9075 | 1.954 ms | 0 - 27 MB | NPU
101
- | EfficientFormer | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 5.589 ms | 0 - 103 MB | NPU
102
- | EfficientFormer | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.784 ms | 0 - 71 MB | NPU
103
- | EfficientFormer | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.634 ms | 0 - 69 MB | NPU
 
 
104
 
105
  ## License
106
  * The license for the original implementation of EfficientFormer can be found
 
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
+ | ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientformer/releases/v0.47.0/efficientformer-onnx-float.zip)
32
+ | ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientformer/releases/v0.47.0/efficientformer-onnx-w8a16.zip)
33
+ | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientformer/releases/v0.47.0/efficientformer-qnn_dlc-float.zip)
34
+ | QNN_DLC | w8a16 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientformer/releases/v0.47.0/efficientformer-qnn_dlc-w8a16.zip)
35
+ | TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientformer/releases/v0.47.0/efficientformer-tflite-float.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[EfficientFormer on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/efficientformer)**.
38
 
 
62
  ## Performance Summary
63
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
64
  |---|---|---|---|---|---|---
65
+ | EfficientFormer | ONNX | float | Snapdragon® X Elite | 1.528 ms | 24 - 24 MB | NPU
66
+ | EfficientFormer | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.95 ms | 0 - 87 MB | NPU
67
+ | EfficientFormer | ONNX | float | Qualcomm® QCS8550 (Proxy) | 1.32 ms | 1 - 5 MB | NPU
68
+ | EfficientFormer | ONNX | float | Qualcomm® QCS9075 | 1.883 ms | 1 - 3 MB | NPU
69
+ | EfficientFormer | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.704 ms | 0 - 46 MB | NPU
70
+ | EfficientFormer | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.609 ms | 1 - 53 MB | NPU
71
+ | EfficientFormer | ONNX | float | Snapdragon® X2 Elite | 0.646 ms | 25 - 25 MB | NPU
72
+ | EfficientFormer | ONNX | w8a16 | Snapdragon® X Elite | 1.661 ms | 12 - 12 MB | NPU
73
+ | EfficientFormer | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 0.962 ms | 0 - 93 MB | NPU
74
+ | EfficientFormer | ONNX | w8a16 | Qualcomm® QCS6490 | 143.031 ms | 19 - 25 MB | CPU
75
+ | EfficientFormer | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 1.401 ms | 0 - 17 MB | NPU
76
+ | EfficientFormer | ONNX | w8a16 | Qualcomm® QCS9075 | 1.631 ms | 0 - 3 MB | NPU
77
+ | EfficientFormer | ONNX | w8a16 | Qualcomm® QCM6690 | 66.257 ms | 12 - 20 MB | CPU
78
+ | EfficientFormer | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 0.647 ms | 0 - 63 MB | NPU
79
+ | EfficientFormer | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 62.871 ms | 22 - 31 MB | CPU
80
+ | EfficientFormer | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.531 ms | 0 - 66 MB | NPU
81
+ | EfficientFormer | ONNX | w8a16 | Snapdragon® X2 Elite | 0.562 ms | 12 - 12 MB | NPU
82
+ | EfficientFormer | QNN_DLC | float | Snapdragon® X Elite | 1.744 ms | 1 - 1 MB | NPU
83
+ | EfficientFormer | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.063 ms | 0 - 80 MB | NPU
84
+ | EfficientFormer | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 4.912 ms | 1 - 45 MB | NPU
85
+ | EfficientFormer | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 1.498 ms | 1 - 2 MB | NPU
86
+ | EfficientFormer | QNN_DLC | float | Qualcomm® QCS9075 | 1.979 ms | 1 - 3 MB | NPU
87
+ | EfficientFormer | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 5.532 ms | 0 - 83 MB | NPU
88
+ | EfficientFormer | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.776 ms | 1 - 48 MB | NPU
89
  | EfficientFormer | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.649 ms | 1 - 49 MB | NPU
90
+ | EfficientFormer | QNN_DLC | float | Snapdragon® X2 Elite | 0.919 ms | 1 - 1 MB | NPU
91
+ | EfficientFormer | QNN_DLC | w8a16 | Snapdragon® X Elite | 1.846 ms | 0 - 0 MB | NPU
92
+ | EfficientFormer | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1.095 ms | 0 - 81 MB | NPU
93
+ | EfficientFormer | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 3.289 ms | 0 - 56 MB | NPU
94
+ | EfficientFormer | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 1.62 ms | 0 - 89 MB | NPU
95
+ | EfficientFormer | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 1.785 ms | 0 - 2 MB | NPU
96
+ | EfficientFormer | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 7.002 ms | 0 - 176 MB | NPU
97
+ | EfficientFormer | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 0.719 ms | 0 - 55 MB | NPU
98
+ | EfficientFormer | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 1.722 ms | 0 - 60 MB | NPU
99
+ | EfficientFormer | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.585 ms | 0 - 59 MB | NPU
100
+ | EfficientFormer | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 0.831 ms | 0 - 0 MB | NPU
101
+ | EfficientFormer | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.048 ms | 0 - 104 MB | NPU
102
+ | EfficientFormer | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 4.91 ms | 0 - 64 MB | NPU
103
+ | EfficientFormer | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 1.505 ms | 0 - 4 MB | NPU
104
+ | EfficientFormer | TFLITE | float | Qualcomm® QCS9075 | 1.969 ms | 0 - 27 MB | NPU
105
+ | EfficientFormer | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 5.534 ms | 0 - 101 MB | NPU
106
+ | EfficientFormer | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.777 ms | 0 - 70 MB | NPU
107
+ | EfficientFormer | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.651 ms | 0 - 68 MB | NPU
108
 
109
  ## License
110
  * The license for the original implementation of EfficientFormer can be found