Hugging Face's logo

qualcomm
/
EfficientViT-l2-cls

Image Classification
PyTorch
backbone
bu_auto
real_time
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
1d515f8
·
verified ·
1 Parent(s): 88e7805

v0.58.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.58.0 for changelog.

Files changed (2) hide show
  1. README.md +48 -45
  2. release_assets.json +4 -4
README.md CHANGED
@@ -17,7 +17,7 @@ pipeline_tag: image-classification
17
  EfficientViT 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.
18
 
19
  This is based on the implementation of EfficientViT-l2-cls found [here](https://github.com/CVHub520/efficientvit).
20
- 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/v0.57.3/src/qai_hub_models/models/efficientvit_l2_cls) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
21
 
22
  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.
23
 
@@ -30,23 +30,23 @@ Below are pre-exported model assets ready for deployment.
30
 
31
  | Runtime | Precision | Chipset | SDK Versions | Download |
32
  |---|---|---|---|---|
33
- | ONNX | float | Universal | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientvit_l2_cls/releases/v0.57.3/efficientvit_l2_cls-onnx-float.zip)
34
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientvit_l2_cls/releases/v0.57.3/efficientvit_l2_cls-qnn_dlc-float.zip)
35
- | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientvit_l2_cls/releases/v0.57.3/efficientvit_l2_cls-tflite-float.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[EfficientViT-l2-cls on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/efficientvit_l2_cls)**.
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/v0.57.3/src/qai_hub_models/models/efficientvit_l2_cls) 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 [EfficientViT-l2-cls on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.57.3/src/qai_hub_models/models/efficientvit_l2_cls) for usage instructions.
50
 
51
  ## Model Details
52
 
@@ -61,45 +61,48 @@ See our repository for [EfficientViT-l2-cls on GitHub](https://github.com/qualco
61
  ## Performance Summary
62
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
63
  |---|---|---|---|---|---|---
64
- | EfficientViT-l2-cls | ONNX | float | Snapdragon® X2 Elite | 3.21 ms | 212 - 212 MB | NPU
65
- | EfficientViT-l2-cls | ONNX | float | Snapdragon® X Elite | 6.616 ms | 148 - 148 MB | NPU
66
- | EfficientViT-l2-cls | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 4.463 ms | 0 - 212 MB | NPU
67
- | EfficientViT-l2-cls | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 13.655 ms | 1 - 185 MB | NPU
68
- | EfficientViT-l2-cls | ONNX | float | Qualcomm® QCS8550 (Proxy) | 6.488 ms | 0 - 163 MB | NPU
69
- | EfficientViT-l2-cls | ONNX | float | Qualcomm® QCS8450 | 13.655 ms | 1 - 185 MB | NPU
70
- | EfficientViT-l2-cls | ONNX | float | Snapdragon® 8 Elite Mobile | 3.622 ms | 0 - 117 MB | NPU
71
- | EfficientViT-l2-cls | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.007 ms | 1 - 112 MB | NPU
72
- | EfficientViT-l2-cls | ONNX | float | Qualcomm® QCS9075 | 7.902 ms | 1 - 46 MB | NPU
73
- | EfficientViT-l2-cls | ONNX | float | Qualcomm® QCS8750 | 3.622 ms | 0 - 117 MB | NPU
74
- | EfficientViT-l2-cls | ONNX | float | Qualcomm® QCS7181 | 6.616 ms | 148 - 148 MB | NPU
75
- | EfficientViT-l2-cls | QNN_DLC | float | Snapdragon® X2 Elite | 3.938 ms | 1 - 1 MB | NPU
76
- | EfficientViT-l2-cls | QNN_DLC | float | Snapdragon® X Elite | 8.11 ms | 1 - 1 MB | NPU
77
- | EfficientViT-l2-cls | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 5.235 ms | 0 - 222 MB | NPU
78
- | EfficientViT-l2-cls | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 14.904 ms | 0 - 190 MB | NPU
79
- | EfficientViT-l2-cls | QNN_DLC | float | Qualcomm® QCS8275 | 24.362 ms | 1 - 108 MB | NPU
80
- | EfficientViT-l2-cls | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 7.774 ms | 1 - 2 MB | NPU
81
- | EfficientViT-l2-cls | QNN_DLC | float | Qualcomm® QCS8450 | 14.904 ms | 0 - 190 MB | NPU
82
- | EfficientViT-l2-cls | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 3.965 ms | 0 - 117 MB | NPU
83
- | EfficientViT-l2-cls | QNN_DLC | float | Qualcomm® SA8295P | 14.71 ms | 1 - 97 MB | NPU
84
- | EfficientViT-l2-cls | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.213 ms | 1 - 115 MB | NPU
85
- | EfficientViT-l2-cls | QNN_DLC | float | Qualcomm® SA7255P | 24.362 ms | 1 - 108 MB | NPU
86
- | EfficientViT-l2-cls | QNN_DLC | float | Qualcomm® QCS9075 | 8.564 ms | 1 - 3 MB | NPU
87
- | EfficientViT-l2-cls | QNN_DLC | float | Qualcomm® QCS8750 | 3.965 ms | 0 - 117 MB | NPU
88
- | EfficientViT-l2-cls | QNN_DLC | float | Qualcomm® QCS7181 | 8.11 ms | 1 - 1 MB | NPU
89
- | EfficientViT-l2-cls | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.205 ms | 0 - 296 MB | NPU
90
- | EfficientViT-l2-cls | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 14.86 ms | 0 - 277 MB | NPU
91
- | EfficientViT-l2-cls | TFLITE | float | Qualcomm® QCS8275 | 24.326 ms | 0 - 179 MB | NPU
92
- | EfficientViT-l2-cls | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 7.825 ms | 0 - 3 MB | NPU
93
- | EfficientViT-l2-cls | TFLITE | float | Qualcomm® SA8775P | 40.994 ms | 0 - 30 MB | GPU
94
- | EfficientViT-l2-cls | TFLITE | float | Qualcomm® SA8650P | 40.994 ms | 0 - 30 MB | GPU
95
- | EfficientViT-l2-cls | TFLITE | float | Qualcomm® SA8255P | 40.994 ms | 0 - 30 MB | GPU
96
- | EfficientViT-l2-cls | TFLITE | float | Qualcomm® QCS8450 | 14.86 ms | 0 - 277 MB | NPU
97
- | EfficientViT-l2-cls | TFLITE | float | Snapdragon® 8 Elite Mobile | 3.96 ms | 0 - 183 MB | NPU
98
- | EfficientViT-l2-cls | TFLITE | float | Qualcomm® SA8295P | 14.653 ms | 0 - 168 MB | NPU
99
- | EfficientViT-l2-cls | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.215 ms | 0 - 187 MB | NPU
100
- | EfficientViT-l2-cls | TFLITE | float | Qualcomm® SA7255P | 24.326 ms | 0 - 179 MB | NPU
101
- | EfficientViT-l2-cls | TFLITE | float | Qualcomm® QCS9075 | 8.48 ms | 0 - 134 MB | NPU
102
- | EfficientViT-l2-cls | TFLITE | float | Qualcomm® QCS8750 | 3.96 ms | 0 - 183 MB | NPU
 
 
 
103
 
104
  ## License
105
  * The license for the original implementation of EfficientViT-l2-cls can be found
 
17
  EfficientViT 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.
18
 
19
  This is based on the implementation of EfficientViT-l2-cls found [here](https://github.com/CVHub520/efficientvit).
20
+ 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/v0.58.0/src/qai_hub_models/models/efficientvit_l2_cls) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
21
 
22
  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.
23
 
 
30
 
31
  | Runtime | Precision | Chipset | SDK Versions | Download |
32
  |---|---|---|---|---|
33
+ | ONNX | float | Universal | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientvit_l2_cls/releases/v0.58.0/efficientvit_l2_cls-onnx-float.zip)
34
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientvit_l2_cls/releases/v0.58.0/efficientvit_l2_cls-qnn_dlc-float.zip)
35
+ | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientvit_l2_cls/releases/v0.58.0/efficientvit_l2_cls-tflite-float.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[EfficientViT-l2-cls on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/efficientvit_l2_cls)**.
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/v0.58.0/src/qai_hub_models/models/efficientvit_l2_cls) 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 [EfficientViT-l2-cls on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.58.0/src/qai_hub_models/models/efficientvit_l2_cls) for usage instructions.
50
 
51
  ## Model Details
52
 
 
61
  ## Performance Summary
62
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
63
  |---|---|---|---|---|---|---
64
+ | EfficientViT-l2-cls | ONNX | float | Snapdragon® X2 Elite | 3.223 ms | 2 - 2 MB | NPU
65
+ | EfficientViT-l2-cls | ONNX | float | Snapdragon® X Elite | 6.597 ms | 131 - 131 MB | NPU
66
+ | EfficientViT-l2-cls | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 4.463 ms | 0 - 225 MB | NPU
67
+ | EfficientViT-l2-cls | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 13.676 ms | 1 - 194 MB | NPU
68
+ | EfficientViT-l2-cls | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 6.437 ms | 1 - 35 MB | NPU
69
+ | EfficientViT-l2-cls | ONNX | float | Qualcomm® QCS8450 | 13.676 ms | 1 - 194 MB | NPU
70
+ | EfficientViT-l2-cls | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 8.008 ms | 0 - 4 MB | NPU
71
+ | EfficientViT-l2-cls | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.035 ms | 0 - 114 MB | NPU
72
+ | EfficientViT-l2-cls | ONNX | float | Snapdragon® 8 Elite Mobile | 3.593 ms | 0 - 118 MB | NPU
73
+ | EfficientViT-l2-cls | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 3.593 ms | 0 - 118 MB | NPU
74
+ | EfficientViT-l2-cls | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 6.597 ms | 131 - 131 MB | NPU
75
+ | EfficientViT-l2-cls | QNN_DLC | float | Snapdragon® X2 Elite | 3.963 ms | 1 - 1 MB | NPU
76
+ | EfficientViT-l2-cls | QNN_DLC | float | Snapdragon® X Elite | 8.107 ms | 1 - 1 MB | NPU
77
+ | EfficientViT-l2-cls | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 5.217 ms | 1 - 225 MB | NPU
78
+ | EfficientViT-l2-cls | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 14.917 ms | 0 - 190 MB | NPU
79
+ | EfficientViT-l2-cls | QNN_DLC | float | Qualcomm® QCS8275 | 24.386 ms | 1 - 108 MB | NPU
80
+ | EfficientViT-l2-cls | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.387 ms | 1 - 275 MB | NPU
81
+ | EfficientViT-l2-cls | QNN_DLC | float | Qualcomm® SA8775P | 9.573 ms | 1 - 108 MB | NPU
82
+ | EfficientViT-l2-cls | QNN_DLC | float | Qualcomm® SA8650P | 9.573 ms | 1 - 108 MB | NPU
83
+ | EfficientViT-l2-cls | QNN_DLC | float | Qualcomm® SA8255P | 9.573 ms | 1 - 108 MB | NPU
84
+ | EfficientViT-l2-cls | QNN_DLC | float | Qualcomm® QCS8450 | 14.917 ms | 0 - 190 MB | NPU
85
+ | EfficientViT-l2-cls | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 9.38 ms | 3 - 5 MB | NPU
86
+ | EfficientViT-l2-cls | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.243 ms | 0 - 112 MB | NPU
87
+ | EfficientViT-l2-cls | QNN_DLC | float | Qualcomm® SA7255P | 24.386 ms | 1 - 108 MB | NPU
88
+ | EfficientViT-l2-cls | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 3.938 ms | 0 - 114 MB | NPU
89
+ | EfficientViT-l2-cls | QNN_DLC | float | Qualcomm® SA8295P | 14.705 ms | 1 - 97 MB | NPU
90
+ | EfficientViT-l2-cls | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 3.938 ms | 0 - 114 MB | NPU
91
+ | EfficientViT-l2-cls | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 8.107 ms | 1 - 1 MB | NPU
92
+ | EfficientViT-l2-cls | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.16 ms | 0 - 296 MB | NPU
93
+ | EfficientViT-l2-cls | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 14.845 ms | 0 - 274 MB | NPU
94
+ | EfficientViT-l2-cls | TFLITE | float | Qualcomm® QCS8275 | 24.251 ms | 0 - 179 MB | NPU
95
+ | EfficientViT-l2-cls | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.405 ms | 0 - 3 MB | NPU
96
+ | EfficientViT-l2-cls | TFLITE | float | Qualcomm® SA8775P | 9.61 ms | 0 - 179 MB | NPU
97
+ | EfficientViT-l2-cls | TFLITE | float | Qualcomm® SA8650P | 9.61 ms | 0 - 179 MB | NPU
98
+ | EfficientViT-l2-cls | TFLITE | float | Qualcomm® SA8255P | 9.61 ms | 0 - 179 MB | NPU
99
+ | EfficientViT-l2-cls | TFLITE | float | Qualcomm® QCS8450 | 14.845 ms | 0 - 274 MB | NPU
100
+ | EfficientViT-l2-cls | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 9.352 ms | 0 - 134 MB | NPU
101
+ | EfficientViT-l2-cls | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.241 ms | 0 - 187 MB | NPU
102
+ | EfficientViT-l2-cls | TFLITE | float | Qualcomm® SA7255P | 24.251 ms | 0 - 179 MB | NPU
103
+ | EfficientViT-l2-cls | TFLITE | float | Snapdragon® 8 Elite Mobile | 3.939 ms | 0 - 184 MB | NPU
104
+ | EfficientViT-l2-cls | TFLITE | float | Qualcomm® SA8295P | 14.661 ms | 0 - 168 MB | NPU
105
+ | EfficientViT-l2-cls | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 3.939 ms | 0 - 184 MB | NPU
106
 
107
  ## License
108
  * The license for the original implementation of EfficientViT-l2-cls can be found
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.57.3",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
@@ -8,20 +8,20 @@
8
  "qairt": "2.45.0.260326154327",
9
  "litert": "1.4.4"
10
  },
11
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientvit_l2_cls/releases/v0.57.3/efficientvit_l2_cls-tflite-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/efficientvit_l2_cls/releases/v0.57.3/efficientvit_l2_cls-qnn_dlc-float.zip"
18
  },
19
  "onnx": {
20
  "tool_versions": {
21
  "qairt": "2.45.0.260326154327",
22
  "onnx_runtime": "1.25.0"
23
  },
24
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientvit_l2_cls/releases/v0.57.3/efficientvit_l2_cls-onnx-float.zip"
25
  }
26
  }
27
  }
 
1
  {
2
+ "version": "0.58.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
 
8
  "qairt": "2.45.0.260326154327",
9
  "litert": "1.4.4"
10
  },
11
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientvit_l2_cls/releases/v0.58.0/efficientvit_l2_cls-tflite-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/efficientvit_l2_cls/releases/v0.58.0/efficientvit_l2_cls-qnn_dlc-float.zip"
18
  },
19
  "onnx": {
20
  "tool_versions": {
21
  "qairt": "2.45.0.260326154327",
22
  "onnx_runtime": "1.25.0"
23
  },
24
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientvit_l2_cls/releases/v0.58.0/efficientvit_l2_cls-onnx-float.zip"
25
  }
26
  }
27
  }