Hugging Face's logo

qualcomm
/
ConvNext-Base

Image Classification
PyTorch
bu_auto
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
122bb8b
·
verified ·
1 Parent(s): eb005e8

v0.49.1

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.49.1 for changelog.

Files changed (1) hide show
  1. README.md +53 -53
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/main/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
 
@@ -28,25 +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 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/convnext_base/releases/v0.48.0/convnext_base-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/convnext_base/releases/v0.48.0/convnext_base-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/convnext_base/releases/v0.48.0/convnext_base-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/convnext_base/releases/v0.48.0/convnext_base-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/convnext_base/releases/v0.48.0/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/main/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/main/qai_hub_models/models/convnext_base) for usage instructions.
50
 
51
  ## Model Details
52
 
@@ -62,51 +62,51 @@ See our repository for [ConvNext-Base on GitHub](https://github.com/qualcomm/ai-
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 | 3.518 ms | 176 - 176 MB | NPU
66
- | ConvNext-Base | ONNX | float | Snapdragon® X Elite | 7.476 ms | 175 - 175 MB | NPU
67
- | ConvNext-Base | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.289 ms | 0 - 352 MB | NPU
68
- | ConvNext-Base | ONNX | float | Qualcomm® QCS8550 (Proxy) | 7.139 ms | 0 - 195 MB | NPU
69
- | ConvNext-Base | ONNX | float | Qualcomm® QCS9075 | 11.123 ms | 0 - 4 MB | NPU
70
- | ConvNext-Base | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.118 ms | 0 - 283 MB | NPU
71
- | ConvNext-Base | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.159 ms | 1 - 285 MB | NPU
72
- | ConvNext-Base | ONNX | w8a16 | Snapdragon® X2 Elite | 2.773 ms | 90 - 90 MB | NPU
73
- | ConvNext-Base | ONNX | w8a16 | Snapdragon® X Elite | 6.472 ms | 90 - 90 MB | NPU
74
- | ConvNext-Base | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 4.384 ms | 0 - 273 MB | NPU
75
- | ConvNext-Base | ONNX | w8a16 | Qualcomm® QCS6490 | 1100.408 ms | 32 - 64 MB | CPU
76
- | ConvNext-Base | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 6.177 ms | 0 - 100 MB | NPU
77
- | ConvNext-Base | ONNX | w8a16 | Qualcomm® QCS9075 | 5.89 ms | 0 - 3 MB | NPU
78
- | ConvNext-Base | ONNX | w8a16 | Qualcomm® QCM6690 | 633.124 ms | 69 - 82 MB | CPU
79
- | ConvNext-Base | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 3.187 ms | 0 - 209 MB | NPU
80
- | ConvNext-Base | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 603.165 ms | 49 - 62 MB | CPU
81
- | ConvNext-Base | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.597 ms | 0 - 223 MB | NPU
82
- | ConvNext-Base | QNN_DLC | float | Snapdragon® X2 Elite | 4.422 ms | 1 - 1 MB | NPU
83
- | ConvNext-Base | QNN_DLC | float | Snapdragon® X Elite | 8.613 ms | 1 - 1 MB | NPU
84
- | ConvNext-Base | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 6.034 ms | 0 - 348 MB | NPU
85
- | ConvNext-Base | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 42.213 ms | 1 - 280 MB | NPU
86
- | ConvNext-Base | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 8.212 ms | 1 - 3 MB | NPU
87
- | ConvNext-Base | QNN_DLC | float | Qualcomm® QCS9075 | 12.353 ms | 1 - 3 MB | NPU
88
- | ConvNext-Base | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 20.741 ms | 0 - 338 MB | NPU
89
- | ConvNext-Base | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.664 ms | 0 - 279 MB | NPU
90
- | ConvNext-Base | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.56 ms | 1 - 284 MB | NPU
91
- | ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 3.055 ms | 0 - 0 MB | NPU
92
- | ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® X Elite | 6.279 ms | 0 - 0 MB | NPU
93
- | ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 4.084 ms | 0 - 247 MB | NPU
94
- | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® QCS6490 | 23.773 ms | 0 - 2 MB | NPU
95
- | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 14.62 ms | 0 - 198 MB | NPU
96
- | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 5.908 ms | 0 - 261 MB | NPU
97
- | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 6.128 ms | 0 - 2 MB | NPU
98
- | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 75.526 ms | 0 - 394 MB | NPU
99
- | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® QCS8450 (Proxy) | 8.925 ms | 0 - 245 MB | NPU
100
- | ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 3.307 ms | 0 - 191 MB | NPU
101
- | ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 7.844 ms | 0 - 248 MB | NPU
102
- | ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.526 ms | 0 - 200 MB | NPU
103
- | ConvNext-Base | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.451 ms | 0 - 345 MB | NPU
104
- | ConvNext-Base | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 40.909 ms | 0 - 273 MB | NPU
105
- | ConvNext-Base | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 7.26 ms | 0 - 2 MB | NPU
106
- | ConvNext-Base | TFLITE | float | Qualcomm® QCS9075 | 11.448 ms | 0 - 177 MB | NPU
107
- | ConvNext-Base | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 19.676 ms | 0 - 329 MB | NPU
108
- | ConvNext-Base | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.116 ms | 0 - 276 MB | NPU
109
- | ConvNext-Base | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.157 ms | 0 - 278 MB | NPU
110
 
111
  ## License
112
  * 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/tree/v0.49.1/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 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/convnext_base/releases/v0.49.1/convnext_base-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/convnext_base/releases/v0.49.1/convnext_base-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/convnext_base/releases/v0.49.1/convnext_base-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/convnext_base/releases/v0.49.1/convnext_base-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/convnext_base/releases/v0.49.1/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/tree/v0.49.1/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/tree/v0.49.1/qai_hub_models/models/convnext_base) for usage instructions.
50
 
51
  ## Model Details
52
 
 
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® 8 Elite Gen 5 Mobile | 3.161 ms | 1 - 285 MB | NPU
66
+ | ConvNext-Base | ONNX | float | Snapdragon® X2 Elite | 3.536 ms | 176 - 176 MB | NPU
67
+ | ConvNext-Base | ONNX | float | Snapdragon® X Elite | 7.488 ms | 175 - 175 MB | NPU
68
+ | ConvNext-Base | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.314 ms | 0 - 350 MB | NPU
69
+ | ConvNext-Base | ONNX | float | Qualcomm® QCS8550 (Proxy) | 7.155 ms | 0 - 195 MB | NPU
70
+ | ConvNext-Base | ONNX | float | Qualcomm® QCS9075 | 11.075 ms | 0 - 4 MB | NPU
71
+ | ConvNext-Base | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.137 ms | 0 - 283 MB | NPU
72
+ | ConvNext-Base | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.589 ms | 0 - 224 MB | NPU
73
+ | ConvNext-Base | ONNX | w8a16 | Snapdragon® X2 Elite | 2.77 ms | 90 - 90 MB | NPU
74
+ | ConvNext-Base | ONNX | w8a16 | Snapdragon® X Elite | 6.449 ms | 90 - 90 MB | NPU
75
+ | ConvNext-Base | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 4.373 ms | 0 - 269 MB | NPU
76
+ | ConvNext-Base | ONNX | w8a16 | Qualcomm® QCS6490 | 1091.433 ms | 32 - 63 MB | CPU
77
+ | ConvNext-Base | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 6.193 ms | 0 - 103 MB | NPU
78
+ | ConvNext-Base | ONNX | w8a16 | Qualcomm® QCS9075 | 5.896 ms | 0 - 3 MB | NPU
79
+ | ConvNext-Base | ONNX | w8a16 | Qualcomm® QCM6690 | 634.065 ms | 43 - 57 MB | CPU
80
+ | ConvNext-Base | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 3.212 ms | 0 - 210 MB | NPU
81
+ | ConvNext-Base | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 607.014 ms | 68 - 83 MB | CPU
82
+ | ConvNext-Base | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.542 ms | 1 - 283 MB | NPU
83
+ | ConvNext-Base | QNN_DLC | float | Snapdragon® X2 Elite | 4.418 ms | 1 - 1 MB | NPU
84
+ | ConvNext-Base | QNN_DLC | float | Snapdragon® X Elite | 8.601 ms | 1 - 1 MB | NPU
85
+ | ConvNext-Base | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 6.034 ms | 0 - 349 MB | NPU
86
+ | ConvNext-Base | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 42.216 ms | 1 - 280 MB | NPU
87
+ | ConvNext-Base | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 8.222 ms | 1 - 3 MB | NPU
88
+ | ConvNext-Base | QNN_DLC | float | Qualcomm® QCS9075 | 12.066 ms | 1 - 3 MB | NPU
89
+ | ConvNext-Base | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 20.621 ms | 0 - 336 MB | NPU
90
+ | ConvNext-Base | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.644 ms | 1 - 281 MB | NPU
91
+ | ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.522 ms | 0 - 200 MB | NPU
92
+ | ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 3.025 ms | 0 - 0 MB | NPU
93
+ | ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® X Elite | 6.289 ms | 0 - 0 MB | NPU
94
+ | ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 4.091 ms | 0 - 248 MB | NPU
95
+ | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® QCS6490 | 23.862 ms | 2 - 4 MB | NPU
96
+ | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 14.601 ms | 0 - 198 MB | NPU
97
+ | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 5.924 ms | 0 - 3 MB | NPU
98
+ | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 6.132 ms | 0 - 2 MB | NPU
99
+ | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 61.117 ms | 0 - 394 MB | NPU
100
+ | ConvNext-Base | QNN_DLC | w8a16 | Qualcomm® QCS8450 (Proxy) | 8.985 ms | 0 - 245 MB | NPU
101
+ | ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 3.277 ms | 0 - 189 MB | NPU
102
+ | ConvNext-Base | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 7.775 ms | 0 - 248 MB | NPU
103
+ | ConvNext-Base | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.156 ms | 0 - 278 MB | NPU
104
+ | ConvNext-Base | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.442 ms | 0 - 346 MB | NPU
105
+ | ConvNext-Base | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 40.92 ms | 0 - 273 MB | NPU
106
+ | ConvNext-Base | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 7.243 ms | 0 - 2 MB | NPU
107
+ | ConvNext-Base | TFLITE | float | Qualcomm® QCS9075 | 11.514 ms | 0 - 177 MB | NPU
108
+ | ConvNext-Base | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 19.705 ms | 0 - 331 MB | NPU
109
+ | ConvNext-Base | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.13 ms | 0 - 277 MB | NPU
110
 
111
  ## License
112
  * The license for the original implementation of ConvNext-Base can be found