Hugging Face's logo

qualcomm
/
OpenAI-Clip

Image Classification
PyTorch
foundation
android
Model card Files
xet
 Community
1
qaihm-bot commited on
Commit
568191e
·
verified ·
1 Parent(s): ef7acd1

v0.63.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.63.0 for changelog.

Files changed (2) hide show
  1. README.md +77 -80
  2. release_assets.json +11 -11
README.md CHANGED
@@ -15,7 +15,7 @@ pipeline_tag: image-classification
15
  Contrastive Language-Image Pre-Training (CLIP) uses a ViT like transformer to get visual features and a causal language model to get the text features. Both the text and visual features can then be used for a variety of zero-shot learning tasks.
16
 
17
  This is based on the implementation of OpenAI-Clip found [here](https://github.com/openai/CLIP/).
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/v0.62.2/src/qai_hub_models/models/openai_clip) 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 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/openai_clip/releases/v0.62.2/openai_clip-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/openai_clip/releases/v0.62.2/openai_clip-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/openai_clip/releases/v0.62.2/openai_clip-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/openai_clip/releases/v0.62.2/openai_clip-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/openai_clip/releases/v0.62.2/openai_clip-tflite-float.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[OpenAI-Clip on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/openai_clip)**.
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/v0.62.2/src/qai_hub_models/models/openai_clip) 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 [OpenAI-Clip on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.62.2/src/qai_hub_models/models/openai_clip) for usage instructions.
50
 
51
  ## Model Details
52
 
@@ -62,82 +62,79 @@ See our repository for [OpenAI-Clip on GitHub](https://github.com/qualcomm/ai-hu
62
  ## Performance Summary
63
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
64
  |---|---|---|---|---|---|---
65
- | OpenAI-Clip | ONNX | float | Snapdragon® X2 Elite | 15.006 ms | 2 - 2 MB | NPU
66
- | OpenAI-Clip | ONNX | float | Snapdragon® X Elite | 33.203 ms | 295 - 295 MB | NPU
67
- | OpenAI-Clip | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 21.524 ms | 0 - 1185 MB | NPU
68
- | OpenAI-Clip | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 47.606 ms | 1 - 894 MB | NPU
69
- | OpenAI-Clip | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 36.0 ms | 0 - 4 MB | NPU
70
- | OpenAI-Clip | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 31.887 ms | 0 - 323 MB | NPU
71
- | OpenAI-Clip | ONNX | float | Qualcomm® QCS8450 | 47.606 ms | 1 - 894 MB | NPU
72
- | OpenAI-Clip | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 36.741 ms | 0 - 4 MB | NPU
73
- | OpenAI-Clip | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 33.203 ms | 295 - 295 MB | NPU
74
- | OpenAI-Clip | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 16.93 ms | 1 - 957 MB | NPU
75
- | OpenAI-Clip | ONNX | float | Snapdragon® 8 Elite Mobile | 16.93 ms | 1 - 957 MB | NPU
76
- | OpenAI-Clip | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 13.451 ms | 1 - 806 MB | NPU
77
- | OpenAI-Clip | ONNX | w8a16 | Snapdragon® X2 Elite | 13.417 ms | 1 - 1 MB | NPU
78
- | OpenAI-Clip | ONNX | w8a16 | Snapdragon® X Elite | 27.039 ms | 173 - 173 MB | NPU
79
- | OpenAI-Clip | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 18.746 ms | 0 - 753 MB | NPU
80
- | OpenAI-Clip | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 39.685 ms | 1 - 759 MB | NPU
81
- | OpenAI-Clip | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 145.115 ms | 1 - 4 MB | NPU
82
- | OpenAI-Clip | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 24.74 ms | 0 - 4 MB | NPU
83
- | OpenAI-Clip | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 26.287 ms | 0 - 4 MB | NPU
84
- | OpenAI-Clip | ONNX | w8a16 | Qualcomm® QCS8450 | 39.685 ms | 1 - 759 MB | NPU
85
- | OpenAI-Clip | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 25.895 ms | 0 - 3 MB | NPU
86
- | OpenAI-Clip | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 27.039 ms | 173 - 173 MB | NPU
87
- | OpenAI-Clip | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 267.969 ms | 1 - 666 MB | NPU
88
- | OpenAI-Clip | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 37.402 ms | 1 - 670 MB | NPU
89
- | OpenAI-Clip | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 14.826 ms | 0 - 640 MB | NPU
90
- | OpenAI-Clip | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 14.826 ms | 0 - 640 MB | NPU
91
- | OpenAI-Clip | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 12.91 ms | 0 - 684 MB | NPU
92
- | OpenAI-Clip | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 37.402 ms | 1 - 670 MB | NPU
93
- | OpenAI-Clip | QNN_DLC | float | Snapdragon® X2 Elite | 14.729 ms | 1 - 1 MB | NPU
94
- | OpenAI-Clip | QNN_DLC | float | Snapdragon® X Elite | 33.367 ms | 1 - 1 MB | NPU
95
- | OpenAI-Clip | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 21.882 ms | 1 - 927 MB | NPU
96
- | OpenAI-Clip | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 46.662 ms | 0 - 855 MB | NPU
97
- | OpenAI-Clip | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 36.472 ms | 1 - 4 MB | NPU
98
- | OpenAI-Clip | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 31.561 ms | 1 - 496 MB | NPU
99
- | OpenAI-Clip | QNN_DLC | float | Qualcomm® SA8775P | 36.675 ms | 1 - 700 MB | NPU
 
100
  | OpenAI-Clip | QNN_DLC | float | Qualcomm® SA8650P | 36.675 ms | 1 - 700 MB | NPU
101
  | OpenAI-Clip | QNN_DLC | float | Qualcomm® SA8255P | 36.675 ms | 1 - 700 MB | NPU
102
- | OpenAI-Clip | QNN_DLC | float | Qualcomm® QCS8450 | 46.662 ms | 0 - 855 MB | NPU
103
- | OpenAI-Clip | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 37.141 ms | 1 - 3 MB | NPU
104
- | OpenAI-Clip | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 33.367 ms | 1 - 1 MB | NPU
105
- | OpenAI-Clip | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 17.263 ms | 0 - 694 MB | NPU
106
- | OpenAI-Clip | QNN_DLC | float | Qualcomm® SA7255P | 99.039 ms | 1 - 704 MB | NPU
107
- | OpenAI-Clip | QNN_DLC | float | Qualcomm® SA8295P | 38.463 ms | 1 - 798 MB | NPU
108
- | OpenAI-Clip | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 17.263 ms | 0 - 694 MB | NPU
109
- | OpenAI-Clip | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 13.35 ms | 0 - 703 MB | NPU
110
- | OpenAI-Clip | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 14.418 ms | 0 - 0 MB | NPU
111
- | OpenAI-Clip | QNN_DLC | w8a16 | Snapdragon® X Elite | 33.348 ms | 0 - 0 MB | NPU
112
- | OpenAI-Clip | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 22.824 ms | 0 - 747 MB | NPU
113
- | OpenAI-Clip | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 30.108 ms | 0 - 3 MB | NPU
114
- | OpenAI-Clip | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 32.881 ms | 0 - 665 MB | NPU
115
- | OpenAI-Clip | QNN_DLC | w8a16 | Qualcomm® SA8775P | 32.453 ms | 0 - 603 MB | NPU
116
- | OpenAI-Clip | QNN_DLC | w8a16 | Qualcomm® SA8650P | 32.453 ms | 0 - 603 MB | NPU
117
- | OpenAI-Clip | QNN_DLC | w8a16 | Qualcomm® SA8255P | 32.453 ms | 0 - 603 MB | NPU
118
- | OpenAI-Clip | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 32.143 ms | 0 - 2 MB | NPU
119
- | OpenAI-Clip | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 33.348 ms | 0 - 0 MB | NPU
120
- | OpenAI-Clip | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 446.478 ms | 0 - 687 MB | NPU
121
- | OpenAI-Clip | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 41.615 ms | 0 - 657 MB | NPU
122
- | OpenAI-Clip | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 18.359 ms | 0 - 633 MB | NPU
123
- | OpenAI-Clip | QNN_DLC | w8a16 | Qualcomm® SA7255P | 67.742 ms | 1 - 604 MB | NPU
124
- | OpenAI-Clip | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 18.359 ms | 0 - 633 MB | NPU
125
- | OpenAI-Clip | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 14.479 ms | 0 - 677 MB | NPU
126
- | OpenAI-Clip | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 41.615 ms | 0 - 657 MB | NPU
127
- | OpenAI-Clip | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 21.756 ms | 0 - 898 MB | NPU
128
- | OpenAI-Clip | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 40.291 ms | 0 - 906 MB | NPU
129
- | OpenAI-Clip | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 35.022 ms | 0 - 297 MB | NPU
130
- | OpenAI-Clip | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 31.532 ms | 0 - 4 MB | NPU
131
- | OpenAI-Clip | TFLITE | float | Qualcomm® SA8775P | 35.976 ms | 0 - 670 MB | NPU
132
  | OpenAI-Clip | TFLITE | float | Qualcomm® SA8650P | 35.976 ms | 0 - 670 MB | NPU
133
  | OpenAI-Clip | TFLITE | float | Qualcomm® SA8255P | 35.976 ms | 0 - 670 MB | NPU
134
- | OpenAI-Clip | TFLITE | float | Qualcomm® QCS8450 | 40.291 ms | 0 - 906 MB | NPU
135
- | OpenAI-Clip | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 36.589 ms | 0 - 296 MB | NPU
136
- | OpenAI-Clip | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 17.215 ms | 0 - 693 MB | NPU
137
- | OpenAI-Clip | TFLITE | float | Qualcomm® SA7255P | 95.568 ms | 0 - 665 MB | NPU
138
- | OpenAI-Clip | TFLITE | float | Qualcomm® SA8295P | 38.34 ms | 0 - 621 MB | NPU
139
- | OpenAI-Clip | TFLITE | float | Snapdragon® 8 Elite Mobile | 17.215 ms | 0 - 693 MB | NPU
140
- | OpenAI-Clip | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 13.028 ms | 0 - 537 MB | NPU
141
 
142
  ## License
143
  * The license for the original implementation of OpenAI-Clip can be found
 
15
  Contrastive Language-Image Pre-Training (CLIP) uses a ViT like transformer to get visual features and a causal language model to get the text features. Both the text and visual features can then be used for a variety of zero-shot learning tasks.
16
 
17
  This is based on the implementation of OpenAI-Clip found [here](https://github.com/openai/CLIP/).
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/v0.63.0/src/qai_hub_models/models/openai_clip) 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 2.50, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/openai_clip/releases/v0.63.0/openai_clip-onnx-float.zip)
32
+ | ONNX | w8a16 | Universal | QAIRT 2.50, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/openai_clip/releases/v0.63.0/openai_clip-onnx-w8a16.zip)
33
+ | QNN_DLC | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/openai_clip/releases/v0.63.0/openai_clip-qnn_dlc-float.zip)
34
+ | QNN_DLC | w8a16 | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/openai_clip/releases/v0.63.0/openai_clip-qnn_dlc-w8a16.zip)
35
+ | TFLITE | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/openai_clip/releases/v0.63.0/openai_clip-tflite-float.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[OpenAI-Clip on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/openai_clip)**.
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/v0.63.0/src/qai_hub_models/models/openai_clip) 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 [OpenAI-Clip on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/openai_clip) 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
+ | OpenAI-Clip | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 13.245 ms | 1 - 613 MB | NPU
66
+ | OpenAI-Clip | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 16.662 ms | 0 - 602 MB | NPU
67
+ | OpenAI-Clip | ONNX | float | Snapdragon® X2 Elite | 13.948 ms | 2 - 2 MB | NPU
68
+ | OpenAI-Clip | ONNX | float | Snapdragon® X Elite | 32.635 ms | 294 - 294 MB | NPU
69
+ | OpenAI-Clip | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 21.83 ms | 1 - 992 MB | NPU
70
+ | OpenAI-Clip | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 41.33 ms | 1 - 848 MB | NPU
71
+ | OpenAI-Clip | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 35.502 ms | 0 - 5 MB | NPU
72
+ | OpenAI-Clip | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 31.987 ms | 0 - 322 MB | NPU
73
+ | OpenAI-Clip | ONNX | float | Qualcomm® QCS8450 | 41.33 ms | 1 - 848 MB | NPU
74
+ | OpenAI-Clip | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 36.392 ms | 1 - 5 MB | NPU
75
+ | OpenAI-Clip | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 32.635 ms | 294 - 294 MB | NPU
76
+ | OpenAI-Clip | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 16.662 ms | 0 - 602 MB | NPU
77
+ | OpenAI-Clip | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 11.485 ms | 0 - 658 MB | NPU
78
+ | OpenAI-Clip | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 14.918 ms | 0 - 620 MB | NPU
79
+ | OpenAI-Clip | ONNX | w8a16 | Snapdragon® X2 Elite | 11.929 ms | 1 - 1 MB | NPU
80
+ | OpenAI-Clip | ONNX | w8a16 | Snapdragon® X Elite | 25.222 ms | 173 - 173 MB | NPU
81
+ | OpenAI-Clip | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 17.896 ms | 0 - 739 MB | NPU
82
+ | OpenAI-Clip | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 34.933 ms | 0 - 740 MB | NPU
83
+ | OpenAI-Clip | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 103.718 ms | 3 - 6 MB | NPU
84
+ | OpenAI-Clip | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 23.545 ms | 0 - 5 MB | NPU
85
+ | OpenAI-Clip | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 24.639 ms | 0 - 195 MB | NPU
86
+ | OpenAI-Clip | ONNX | w8a16 | Qualcomm® QCS8450 | 34.933 ms | 0 - 740 MB | NPU
87
+ | OpenAI-Clip | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 24.63 ms | 0 - 4 MB | NPU
88
+ | OpenAI-Clip | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 25.222 ms | 173 - 173 MB | NPU
89
+ | OpenAI-Clip | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 334.61 ms | 0 - 690 MB | NPU
90
+ | OpenAI-Clip | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 37.089 ms | 1 - 638 MB | NPU
91
+ | OpenAI-Clip | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 14.918 ms | 0 - 620 MB | NPU
92
+ | OpenAI-Clip | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 37.089 ms | 1 - 638 MB | NPU
93
+ | OpenAI-Clip | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 13.098 ms | 0 - 489 MB | NPU
94
+ | OpenAI-Clip | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 16.747 ms | 1 - 483 MB | NPU
95
+ | OpenAI-Clip | QNN_DLC | float | Snapdragon® X2 Elite | 14.143 ms | 1 - 1 MB | NPU
96
+ | OpenAI-Clip | QNN_DLC | float | Snapdragon® X Elite | 33.128 ms | 1 - 1 MB | NPU
97
+ | OpenAI-Clip | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 21.394 ms | 0 - 688 MB | NPU
98
+ | OpenAI-Clip | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 37.296 ms | 1 - 815 MB | NPU
99
+ | OpenAI-Clip | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 35.973 ms | 1 - 4 MB | NPU
100
+ | OpenAI-Clip | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 31.39 ms | 1 - 3 MB | NPU
101
  | OpenAI-Clip | QNN_DLC | float | Qualcomm® SA8650P | 36.675 ms | 1 - 700 MB | NPU
102
  | OpenAI-Clip | QNN_DLC | float | Qualcomm® SA8255P | 36.675 ms | 1 - 700 MB | NPU
103
+ | OpenAI-Clip | QNN_DLC | float | Qualcomm® QCS8450 | 37.296 ms | 1 - 815 MB | NPU
104
+ | OpenAI-Clip | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 36.419 ms | 3 - 5 MB | NPU
105
+ | OpenAI-Clip | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 33.128 ms | 1 - 1 MB | NPU
106
+ | OpenAI-Clip | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 16.747 ms | 1 - 483 MB | NPU
107
+ | OpenAI-Clip | QNN_DLC | float | Qualcomm® SA8295P | 37.723 ms | 1 - 591 MB | NPU
108
+ | OpenAI-Clip | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 11.506 ms | 0 - 628 MB | NPU
109
+ | OpenAI-Clip | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 15.226 ms | 0 - 591 MB | NPU
110
+ | OpenAI-Clip | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 12.1 ms | 0 - 0 MB | NPU
111
+ | OpenAI-Clip | QNN_DLC | w8a16 | Snapdragon® X Elite | 28.154 ms | 0 - 0 MB | NPU
112
+ | OpenAI-Clip | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 18.724 ms | 0 - 702 MB | NPU
113
+ | OpenAI-Clip | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 24.827 ms | 0 - 3 MB | NPU
114
+ | OpenAI-Clip | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 27.141 ms | 0 - 440 MB | NPU
115
+ | OpenAI-Clip | QNN_DLC | w8a16 | Qualcomm® SA8775P | 26.821 ms | 0 - 566 MB | NPU
116
+ | OpenAI-Clip | QNN_DLC | w8a16 | Qualcomm® SA8650P | 26.821 ms | 0 - 566 MB | NPU
117
+ | OpenAI-Clip | QNN_DLC | w8a16 | Qualcomm® SA8255P | 26.821 ms | 0 - 566 MB | NPU
118
+ | OpenAI-Clip | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 27.154 ms | 0 - 3 MB | NPU
119
+ | OpenAI-Clip | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 28.154 ms | 0 - 0 MB | NPU
120
+ | OpenAI-Clip | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 432.665 ms | 1 - 693 MB | NPU
121
+ | OpenAI-Clip | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 37.332 ms | 0 - 611 MB | NPU
122
+ | OpenAI-Clip | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 15.226 ms | 0 - 591 MB | NPU
123
+ | OpenAI-Clip | QNN_DLC | w8a16 | Qualcomm® SA7255P | 58.663 ms | 0 - 564 MB | NPU
124
+ | OpenAI-Clip | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 37.332 ms | 0 - 611 MB | NPU
125
+ | OpenAI-Clip | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 12.822 ms | 0 - 499 MB | NPU
126
+ | OpenAI-Clip | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 17.003 ms | 0 - 490 MB | NPU
127
+ | OpenAI-Clip | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 21.13 ms | 0 - 693 MB | NPU
128
+ | OpenAI-Clip | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 36.247 ms | 0 - 677 MB | NPU
129
+ | OpenAI-Clip | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 34.563 ms | 0 - 297 MB | NPU
130
+ | OpenAI-Clip | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 30.974 ms | 0 - 3 MB | NPU
 
 
131
  | OpenAI-Clip | TFLITE | float | Qualcomm® SA8650P | 35.976 ms | 0 - 670 MB | NPU
132
  | OpenAI-Clip | TFLITE | float | Qualcomm® SA8255P | 35.976 ms | 0 - 670 MB | NPU
133
+ | OpenAI-Clip | TFLITE | float | Qualcomm® QCS8450 | 36.247 ms | 0 - 677 MB | NPU
134
+ | OpenAI-Clip | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 35.657 ms | 0 - 297 MB | NPU
135
+ | OpenAI-Clip | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 17.003 ms | 0 - 490 MB | NPU
136
+ | OpenAI-Clip | TFLITE | float | Qualcomm® SA7255P | 748.41 ms | 11 - 35 MB | CPU
137
+ | OpenAI-Clip | TFLITE | float | Qualcomm® SA8295P | 37.294 ms | 0 - 441 MB | NPU
 
 
138
 
139
  ## License
140
  * The license for the original implementation of OpenAI-Clip can be found
release_assets.json CHANGED
@@ -1,26 +1,26 @@
1
  {
2
- "version": "0.62.2",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
6
  "onnx": {
7
  "tool_versions": {
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/openai_clip/releases/v0.62.2/openai_clip-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/openai_clip/releases/v0.62.2/openai_clip-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/openai_clip/releases/v0.62.2/openai_clip-tflite-float.zip"
24
  }
25
  }
26
  },
@@ -28,16 +28,16 @@
28
  "universal_assets": {
29
  "onnx": {
30
  "tool_versions": {
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/openai_clip/releases/v0.62.2/openai_clip-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/openai_clip/releases/v0.62.2/openai_clip-qnn_dlc-w8a16.zip"
41
  }
42
  }
43
  }
 
1
  {
2
+ "version": "0.63.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
6
  "onnx": {
7
  "tool_versions": {
8
+ "qairt": "2.50.0.260828221209",
9
  "onnx_runtime": "1.27.1"
10
  },
11
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/openai_clip/releases/v0.63.0/openai_clip-onnx-float.zip"
12
  },
13
  "qnn_dlc": {
14
  "tool_versions": {
15
+ "qairt": "2.50.0.260828221209"
16
  },
17
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/openai_clip/releases/v0.63.0/openai_clip-qnn_dlc-float.zip"
18
  },
19
  "tflite": {
20
  "tool_versions": {
21
+ "qairt": "2.50.0.260828221209"
22
  },
23
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/openai_clip/releases/v0.63.0/openai_clip-tflite-float.zip"
24
  }
25
  }
26
  },
 
28
  "universal_assets": {
29
  "onnx": {
30
  "tool_versions": {
31
+ "qairt": "2.50.0.260828221209",
32
  "onnx_runtime": "1.27.1"
33
  },
34
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/openai_clip/releases/v0.63.0/openai_clip-onnx-w8a16.zip"
35
  },
36
  "qnn_dlc": {
37
  "tool_versions": {
38
+ "qairt": "2.50.0.260828221209"
39
  },
40
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/openai_clip/releases/v0.63.0/openai_clip-qnn_dlc-w8a16.zip"
41
  }
42
  }
43
  }