Hugging Face's logo

qualcomm
/
ConvNext-Base

Image Classification
PyTorch
bu_auto
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
2db064f
·
verified ·
1 Parent(s): cc54a19

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 +91 -84
  2. release_assets.json +6 -6
README.md CHANGED
@@ -15,7 +15,7 @@ pipeline_tag: image-classification
15
  ConvNextBase is a machine learning model that can classify images from the Imagenet dataset. It can also be used as a backbone in building more complex models for specific use cases.
16
 
17
  This is based on the implementation of ConvNext-Base found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/convnext.py).
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/v0.59.0/src/qai_hub_models/models/convnext_base) 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
 
@@ -28,115 +28,122 @@ Below are pre-exported model assets ready for deployment.
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
- | 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/convnext_base/releases/v0.59.0/convnext_base-onnx-float.zip)
32
- | ONNX | w8a16 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/convnext_base/releases/v0.59.0/convnext_base-onnx-w8a16.zip)
33
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/convnext_base/releases/v0.59.0/convnext_base-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/convnext_base/releases/v0.59.0/convnext_base-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/convnext_base/releases/v0.59.0/convnext_base-tflite-float.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[ConvNext-Base on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/convnext_base)**.
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/v0.59.0/src/qai_hub_models/models/convnext_base) 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 [ConvNext-Base on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/convnext_base) for usage instructions.
50
 
51
  ## Model Details
52
 
53
  **Model Type:** Model_use_case.image_classification
54
 
55
  **Model Stats:**
56
- - Model checkpoint: Imagenet
57
  - Input resolution: 224x224
58
- - Number of parameters: 88.6M
59
  - Model size (float): 338 MB
60
  - Model size (w8a16): 88.7 MB
 
61
 
62
  ## Performance Summary
63
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
64
  |---|---|---|---|---|---|---
65
- | ConvNext-Base | ONNX | float | Snapdragon® X2 Elite | 3.491 ms | 2 - 2 MB | NPU
66
- | ConvNext-Base | ONNX | float | Snapdragon® X Elite | 7.229 ms | 176 - 176 MB | NPU
67
- | ConvNext-Base | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.308 ms | 1 - 313 MB | NPU
68
- | ConvNext-Base | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 19.187 ms | 1 - 301 MB | NPU
69
- | ConvNext-Base | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.145 ms | 0 - 194 MB | NPU
70
- | ConvNext-Base | ONNX | float | Qualcomm® QCS8450 | 19.187 ms | 1 - 301 MB | NPU
71
- | ConvNext-Base | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 10.748 ms | 0 - 4 MB | NPU
72
- | ConvNext-Base | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 7.229 ms | 176 - 176 MB | NPU
73
- | ConvNext-Base | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 4.122 ms | 0 - 184 MB | NPU
74
- | ConvNext-Base | ONNX | float | Snapdragon® 8 Elite Mobile | 4.122 ms | 0 - 184 MB | NPU
75
- | ConvNext-Base | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.201 ms | 0 - 185 MB | NPU
76
  | ConvNext-Base | ONNX | w8a16 | Snapdragon® X2 Elite | 2.383 ms | 1 - 1 MB | NPU
77
- | ConvNext-Base | ONNX | w8a16 | Snapdragon® X Elite | 4.973 ms | 90 - 90 MB | NPU
78
- | ConvNext-Base | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 3.455 ms | 0 - 263 MB | NPU
79
- | ConvNext-Base | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 8.154 ms | 0 - 262 MB | NPU
80
- | ConvNext-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 32.943 ms | 0 - 3 MB | NPU
81
- | ConvNext-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.865 ms | 0 - 100 MB | NPU
82
- | ConvNext-Base | ONNX | w8a16 | Qualcomm® QCS8450 | 8.154 ms | 0 - 262 MB | NPU
83
- | ConvNext-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 4.866 ms | 0 - 3 MB | NPU
84
- | ConvNext-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 4.973 ms | 90 - 90 MB | NPU
85
- | ConvNext-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 2.773 ms | 0 - 206 MB | NPU
86
- | ConvNext-Base | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 2.773 ms | 0 - 206 MB | NPU
87
- | ConvNext-Base | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.171 ms | 0 - 226 MB | NPU
88
- | ConvNext-Base | QNN_DLC | float | Snapdragon® X2 Elite | 4.309 ms | 1 - 1 MB | NPU
89
- | ConvNext-Base | QNN_DLC | float | Snapdragon® X Elite | 8.387 ms | 1 - 1 MB | NPU
90
- | ConvNext-Base | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 5.842 ms | 1 - 306 MB | NPU
91
- | ConvNext-Base | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 20.385 ms | 0 - 295 MB | NPU
92
- | ConvNext-Base | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8275 | 41.888 ms | 1 - 180 MB | NPU
93
- | ConvNext-Base | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.947 ms | 1 - 361 MB | NPU
94
- | ConvNext-Base | QNN_DLC | float | Qualcomm® SA8775P | 11.826 ms | 1 - 181 MB | NPU
95
- | ConvNext-Base | QNN_DLC | float | Qualcomm® SA8650P | 11.826 ms | 1 - 181 MB | NPU
96
- | ConvNext-Base | QNN_DLC | float | Qualcomm® SA8255P | 11.826 ms | 1 - 181 MB | NPU
97
- | ConvNext-Base | QNN_DLC | float | Qualcomm® QCS8450 | 20.385 ms | 0 - 295 MB | NPU
98
- | ConvNext-Base | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 11.529 ms | 1 - 3 MB | NPU
99
- | ConvNext-Base | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 8.387 ms | 1 - 1 MB | NPU
100
- | ConvNext-Base | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 4.542 ms | 0 - 180 MB | NPU
101
- | ConvNext-Base | QNN_DLC | float | Qualcomm® SA7255P | 41.888 ms | 1 - 180 MB | NPU
102
- | ConvNext-Base | QNN_DLC | float | Qualcomm® SA8295P | 19.68 ms | 1 - 171 MB | NPU
103
- | ConvNext-Base | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 4.542 ms | 0 - 180 MB | NPU
104
- | ConvNext-Base | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.493 ms | 1 - 187 MB | NPU
105
- | ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 3.074 ms | 0 - 0 MB | NPU
106
- | ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® X Elite | 6.244 ms | 0 - 0 MB | NPU
107
- | ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 4.081 ms | 0 - 251 MB | NPU
108
- | ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® 8 Gen 1 Mobile | 9.257 ms | 0 - 250 MB | NPU
109
- | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 29.847 ms | 0 - 2 MB | NPU
110
- | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8275 | 14.615 ms | 0 - 203 MB | NPU
111
- | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.871 ms | 0 - 2 MB | NPU
112
- | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® SA8775P | 6.194 ms | 0 - 205 MB | NPU
113
- | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® SA8650P | 6.194 ms | 0 - 205 MB | NPU
114
- | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® SA8255P | 6.194 ms | 0 - 205 MB | NPU
115
- | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® QCS8450 | 9.257 ms | 0 - 250 MB | NPU
116
- | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 5.916 ms | 0 - 2 MB | NPU
117
- | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 6.244 ms | 0 - 0 MB | NPU
118
- | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 71.178 ms | 0 - 397 MB | NPU
119
- | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 7.723 ms | 0 - 253 MB | NPU
120
- | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 3.267 ms | 0 - 195 MB | NPU
121
- | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® SA7255P | 14.615 ms | 0 - 203 MB | NPU
122
- | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® SA8295P | 9.393 ms | 0 - 204 MB | NPU
123
- | ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 3.267 ms | 0 - 195 MB | NPU
124
- | ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.568 ms | 0 - 217 MB | NPU
125
- | ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 7.723 ms | 0 - 253 MB | NPU
126
- | ConvNext-Base | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.456 ms | 0 - 304 MB | NPU
127
- | ConvNext-Base | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 19.709 ms | 0 - 290 MB | NPU
128
- | ConvNext-Base | TFLITE | float | Qualcomm® Dragonwing™ QCS8275 | 40.977 ms | 0 - 175 MB | NPU
129
- | ConvNext-Base | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.255 ms | 0 - 2 MB | NPU
130
- | ConvNext-Base | TFLITE | float | Qualcomm® SA8775P | 11.062 ms | 0 - 176 MB | NPU
131
- | ConvNext-Base | TFLITE | float | Qualcomm® SA8650P | 11.062 ms | 0 - 176 MB | NPU
132
- | ConvNext-Base | TFLITE | float | Qualcomm® SA8255P | 11.062 ms | 0 - 176 MB | NPU
133
- | ConvNext-Base | TFLITE | float | Qualcomm® QCS8450 | 19.709 ms | 0 - 290 MB | NPU
134
- | ConvNext-Base | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 11.72 ms | 0 - 177 MB | NPU
135
- | ConvNext-Base | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 4.096 ms | 0 - 178 MB | NPU
136
- | ConvNext-Base | TFLITE | float | Qualcomm® SA7255P | 40.977 ms | 0 - 175 MB | NPU
137
- | ConvNext-Base | TFLITE | float | Qualcomm® SA8295P | 18.786 ms | 0 - 161 MB | NPU
138
- | ConvNext-Base | TFLITE | float | Snapdragon® 8 Elite Mobile | 4.096 ms | 0 - 178 MB | NPU
139
- | ConvNext-Base | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.216 ms | 0 - 180 MB | NPU
 
 
 
 
 
 
 
140
 
141
  ## License
142
  * The license for the original implementation of ConvNext-Base can be found
 
15
  ConvNextBase is a machine learning model that can classify images from the Imagenet dataset. It can also be used as a backbone in building more complex models for specific use cases.
16
 
17
  This is based on the implementation of ConvNext-Base found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/convnext.py).
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/v0.60.0/src/qai_hub_models/models/convnext_base) 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 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/convnext_base/releases/v0.60.0/convnext_base-onnx-float.zip)
32
+ | ONNX | w8a16 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/convnext_base/releases/v0.60.0/convnext_base-onnx-w8a16.zip)
33
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/convnext_base/releases/v0.60.0/convnext_base-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/convnext_base/releases/v0.60.0/convnext_base-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/convnext_base/releases/v0.60.0/convnext_base-tflite-float.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[ConvNext-Base on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/convnext_base)**.
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/v0.60.0/src/qai_hub_models/models/convnext_base) 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 [ConvNext-Base on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/convnext_base) for usage instructions.
50
 
51
  ## Model Details
52
 
53
  **Model Type:** Model_use_case.image_classification
54
 
55
  **Model Stats:**
 
56
  - Input resolution: 224x224
57
+ - Model checkpoint: Imagenet
58
  - Model size (float): 338 MB
59
  - Model size (w8a16): 88.7 MB
60
+ - Number of parameters: 88.6M
61
 
62
  ## Performance Summary
63
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
64
  |---|---|---|---|---|---|---
65
+ | ConvNext-Base | ONNX | float | Snapdragon® X2 Elite | 3.504 ms | 2 - 2 MB | NPU
66
+ | ConvNext-Base | ONNX | float | Snapdragon® X Elite | 7.232 ms | 176 - 176 MB | NPU
67
+ | ConvNext-Base | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.296 ms | 1 - 313 MB | NPU
68
+ | ConvNext-Base | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 19.215 ms | 1 - 301 MB | NPU
69
+ | ConvNext-Base | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.134 ms | 0 - 245 MB | NPU
70
+ | ConvNext-Base | ONNX | float | Qualcomm® QCS8450 | 19.215 ms | 1 - 301 MB | NPU
71
+ | ConvNext-Base | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 10.831 ms | 0 - 4 MB | NPU
72
+ | ConvNext-Base | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 7.232 ms | 176 - 176 MB | NPU
73
+ | ConvNext-Base | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 4.128 ms | 0 - 185 MB | NPU
74
+ | ConvNext-Base | ONNX | float | Snapdragon® 8 Elite Mobile | 4.128 ms | 0 - 185 MB | NPU
75
+ | ConvNext-Base | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.201 ms | 0 - 186 MB | NPU
76
  | ConvNext-Base | ONNX | w8a16 | Snapdragon® X2 Elite | 2.383 ms | 1 - 1 MB | NPU
77
+ | ConvNext-Base | ONNX | w8a16 | Snapdragon® X Elite | 4.977 ms | 91 - 91 MB | NPU
78
+ | ConvNext-Base | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 3.424 ms | 0 - 262 MB | NPU
79
+ | ConvNext-Base | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 8.063 ms | 0 - 260 MB | NPU
80
+ | ConvNext-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 33.134 ms | 0 - 3 MB | NPU
81
+ | ConvNext-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 4.901 ms | 0 - 4 MB | NPU
82
+ | ConvNext-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.867 ms | 0 - 4 MB | NPU
83
+ | ConvNext-Base | ONNX | w8a16 | Qualcomm® QCS8450 | 8.063 ms | 0 - 260 MB | NPU
84
+ | ConvNext-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 4.883 ms | 0 - 3 MB | NPU
85
+ | ConvNext-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 4.977 ms | 91 - 91 MB | NPU
86
+ | ConvNext-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 58.166 ms | 1 - 400 MB | NPU
87
+ | ConvNext-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 6.881 ms | 0 - 261 MB | NPU
88
+ | ConvNext-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 2.778 ms | 0 - 204 MB | NPU
89
+ | ConvNext-Base | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 2.778 ms | 0 - 204 MB | NPU
90
+ | ConvNext-Base | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.173 ms | 0 - 225 MB | NPU
91
+ | ConvNext-Base | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 6.881 ms | 0 - 261 MB | NPU
92
+ | ConvNext-Base | QNN_DLC | float | Snapdragon® X2 Elite | 4.233 ms | 1 - 1 MB | NPU
93
+ | ConvNext-Base | QNN_DLC | float | Snapdragon® X Elite | 8.41 ms | 1 - 1 MB | NPU
94
+ | ConvNext-Base | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 5.874 ms | 0 - 307 MB | NPU
95
+ | ConvNext-Base | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 20.393 ms | 0 - 296 MB | NPU
96
+ | ConvNext-Base | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 12.775 ms | 1 - 4 MB | NPU
97
+ | ConvNext-Base | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 41.893 ms | 1 - 180 MB | NPU
98
+ | ConvNext-Base | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.982 ms | 1 - 2 MB | NPU
99
+ | ConvNext-Base | QNN_DLC | float | Qualcomm® SA8775P | 11.795 ms | 1 - 181 MB | NPU
100
+ | ConvNext-Base | QNN_DLC | float | Qualcomm® SA8650P | 11.795 ms | 1 - 181 MB | NPU
101
+ | ConvNext-Base | QNN_DLC | float | Qualcomm® SA8255P | 11.795 ms | 1 - 181 MB | NPU
102
+ | ConvNext-Base | QNN_DLC | float | Qualcomm® QCS8450 | 20.393 ms | 0 - 296 MB | NPU
103
+ | ConvNext-Base | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 11.653 ms | 1 - 3 MB | NPU
104
+ | ConvNext-Base | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 8.41 ms | 1 - 1 MB | NPU
105
+ | ConvNext-Base | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 4.586 ms | 1 - 183 MB | NPU
106
+ | ConvNext-Base | QNN_DLC | float | Qualcomm® SA7255P | 41.893 ms | 1 - 180 MB | NPU
107
+ | ConvNext-Base | QNN_DLC | float | Qualcomm® SA8295P | 19.676 ms | 1 - 171 MB | NPU
108
+ | ConvNext-Base | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 4.586 ms | 1 - 183 MB | NPU
109
+ | ConvNext-Base | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.55 ms | 1 - 186 MB | NPU
110
+ | ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 3.096 ms | 0 - 0 MB | NPU
111
+ | ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® X Elite | 6.329 ms | 0 - 0 MB | NPU
112
+ | ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 4.074 ms | 0 - 250 MB | NPU
113
+ | ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® 8 Gen 1 Mobile | 9.074 ms | 0 - 250 MB | NPU
114
+ | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 29.883 ms | 0 - 2 MB | NPU
115
+ | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 5.768 ms | 0 - 3 MB | NPU
116
+ | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 14.627 ms | 0 - 204 MB | NPU
117
+ | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.9 ms | 0 - 2 MB | NPU
118
+ | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® SA8775P | 6.2 ms | 0 - 205 MB | NPU
119
+ | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® SA8650P | 6.2 ms | 0 - 205 MB | NPU
120
+ | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® SA8255P | 6.2 ms | 0 - 205 MB | NPU
121
+ | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® QCS8450 | 9.074 ms | 0 - 250 MB | NPU
122
+ | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 5.931 ms | 2 - 4 MB | NPU
123
+ | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 6.329 ms | 0 - 0 MB | NPU
124
+ | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 75.164 ms | 0 - 402 MB | NPU
125
+ | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 7.742 ms | 0 - 256 MB | NPU
126
+ | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 3.256 ms | 0 - 195 MB | NPU
127
+ | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® SA7255P | 14.627 ms | 0 - 204 MB | NPU
128
+ | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® SA8295P | 9.386 ms | 0 - 204 MB | NPU
129
+ | ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 3.256 ms | 0 - 195 MB | NPU
130
+ | ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.573 ms | 0 - 214 MB | NPU
131
+ | ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 7.742 ms | 0 - 256 MB | NPU
132
+ | ConvNext-Base | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.449 ms | 0 - 302 MB | NPU
133
+ | ConvNext-Base | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 19.656 ms | 0 - 292 MB | NPU
134
+ | ConvNext-Base | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 12.179 ms | 0 - 178 MB | NPU
135
+ | ConvNext-Base | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 40.981 ms | 0 - 175 MB | NPU
136
+ | ConvNext-Base | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.311 ms | 0 - 3 MB | NPU
137
+ | ConvNext-Base | TFLITE | float | Qualcomm® SA8775P | 11.074 ms | 0 - 176 MB | NPU
138
+ | ConvNext-Base | TFLITE | float | Qualcomm® SA8650P | 11.074 ms | 0 - 176 MB | NPU
139
+ | ConvNext-Base | TFLITE | float | Qualcomm® SA8255P | 11.074 ms | 0 - 176 MB | NPU
140
+ | ConvNext-Base | TFLITE | float | Qualcomm® QCS8450 | 19.656 ms | 0 - 292 MB | NPU
141
+ | ConvNext-Base | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 10.811 ms | 0 - 177 MB | NPU
142
+ | ConvNext-Base | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 4.091 ms | 0 - 179 MB | NPU
143
+ | ConvNext-Base | TFLITE | float | Qualcomm® SA7255P | 40.981 ms | 0 - 175 MB | NPU
144
+ | ConvNext-Base | TFLITE | float | Qualcomm® SA8295P | 18.78 ms | 0 - 161 MB | NPU
145
+ | ConvNext-Base | TFLITE | float | Snapdragon® 8 Elite Mobile | 4.091 ms | 0 - 179 MB | NPU
146
+ | ConvNext-Base | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.219 ms | 0 - 180 MB | NPU
147
 
148
  ## License
149
  * The license for the original implementation of ConvNext-Base 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/convnext_base/releases/v0.59.0/convnext_base-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/convnext_base/releases/v0.59.0/convnext_base-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/convnext_base/releases/v0.59.0/convnext_base-tflite-float.zip"
24
  }
25
  }
26
  },
@@ -31,13 +31,13 @@
31
  "qairt": "2.45.0.260326154327",
32
  "onnx_runtime": "1.27.1"
33
  },
34
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/convnext_base/releases/v0.59.0/convnext_base-onnx-w8a16.zip"
35
  },
36
  "qnn_dlc": {
37
  "tool_versions": {
38
  "qairt": "2.45.0.260326154327"
39
  },
40
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/convnext_base/releases/v0.59.0/convnext_base-qnn_dlc-w8a16.zip"
41
  }
42
  }
43
  }
 
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/convnext_base/releases/v0.60.0/convnext_base-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/convnext_base/releases/v0.60.0/convnext_base-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/convnext_base/releases/v0.60.0/convnext_base-tflite-float.zip"
24
  }
25
  }
26
  },
 
31
  "qairt": "2.45.0.260326154327",
32
  "onnx_runtime": "1.27.1"
33
  },
34
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/convnext_base/releases/v0.60.0/convnext_base-onnx-w8a16.zip"
35
  },
36
  "qnn_dlc": {
37
  "tool_versions": {
38
  "qairt": "2.45.0.260326154327"
39
  },
40
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/convnext_base/releases/v0.60.0/convnext_base-qnn_dlc-w8a16.zip"
41
  }
42
  }
43
  }