Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -38,62 +38,60 @@ More details on model performance across various devices, can be found
|
|
38 |
|
39 |
| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
40 |
|---|---|---|---|---|---|---|---|---|
|
41 |
-
| CLIPImageEncoder | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 34.
|
42 |
-
| CLIPImageEncoder | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 26.
|
43 |
-
| CLIPImageEncoder | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE |
|
44 |
-
| CLIPImageEncoder | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 20.
|
45 |
-
| CLIPImageEncoder | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE |
|
46 |
-
| CLIPImageEncoder | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN |
|
47 |
-
| CLIPImageEncoder | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE |
|
48 |
-
| CLIPImageEncoder | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 20.
|
49 |
-
| CLIPImageEncoder | SA7255P ADP | SA7255P | TFLITE | 326.
|
50 |
-
| CLIPImageEncoder | SA7255P ADP | SA7255P | QNN | 264.
|
51 |
-
| CLIPImageEncoder | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 34.
|
52 |
-
| CLIPImageEncoder | SA8255 (Proxy) | SA8255P Proxy | QNN | 20.
|
53 |
-
| CLIPImageEncoder | SA8295P ADP | SA8295P | TFLITE | 40.
|
54 |
-
| CLIPImageEncoder | SA8295P ADP | SA8295P | QNN | 30.
|
55 |
-
| CLIPImageEncoder | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 34.
|
56 |
-
| CLIPImageEncoder | SA8650 (Proxy) | SA8650P Proxy | QNN | 20.
|
57 |
-
| CLIPImageEncoder | SA8775P ADP | SA8775P | TFLITE | 42.
|
58 |
-
| CLIPImageEncoder |
|
59 |
-
| CLIPImageEncoder | QCS8450 (Proxy) | QCS8450 Proxy |
|
60 |
-
| CLIPImageEncoder |
|
61 |
-
|
|
62 |
-
| CLIPTextEncoder | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 |
|
63 |
-
| CLIPTextEncoder | Samsung Galaxy
|
64 |
-
| CLIPTextEncoder | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 |
|
65 |
-
| CLIPTextEncoder |
|
66 |
-
| CLIPTextEncoder | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite |
|
67 |
-
| CLIPTextEncoder |
|
68 |
-
| CLIPTextEncoder | QCS8550 (Proxy) | QCS8550 Proxy |
|
69 |
-
| CLIPTextEncoder |
|
70 |
-
| CLIPTextEncoder | SA7255P ADP | SA7255P |
|
71 |
-
| CLIPTextEncoder |
|
72 |
-
| CLIPTextEncoder | SA8255 (Proxy) | SA8255P Proxy |
|
73 |
-
| CLIPTextEncoder |
|
74 |
-
| CLIPTextEncoder | SA8295P ADP | SA8295P |
|
75 |
-
| CLIPTextEncoder |
|
76 |
-
| CLIPTextEncoder | SA8650 (Proxy) | SA8650P Proxy |
|
77 |
-
| CLIPTextEncoder |
|
78 |
-
| CLIPTextEncoder | SA8775P ADP | SA8775P |
|
79 |
-
| CLIPTextEncoder |
|
80 |
-
| CLIPTextEncoder | QCS8450 (Proxy) | QCS8450 Proxy |
|
81 |
-
| CLIPTextEncoder |
|
82 |
-
| CLIPTextEncoder | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 5.099 ms | 0 - 0 MB | FP16 | NPU | Use Export Script |
|
83 |
|
84 |
|
85 |
|
86 |
|
87 |
## Installation
|
88 |
|
89 |
-
This model can be installed as a Python package via pip.
|
90 |
|
|
|
91 |
```bash
|
92 |
-
pip install "qai-hub-models[
|
93 |
```
|
94 |
|
95 |
|
96 |
-
|
97 |
## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
|
98 |
|
99 |
Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
|
@@ -144,8 +142,8 @@ Profiling Results
|
|
144 |
CLIPImageEncoder
|
145 |
Device : Samsung Galaxy S23 (13)
|
146 |
Runtime : TFLITE
|
147 |
-
Estimated inference time (ms) : 34.
|
148 |
-
Estimated peak memory usage (MB): [0,
|
149 |
Total # Ops : 659
|
150 |
Compute Unit(s) : NPU (659 ops)
|
151 |
|
@@ -153,8 +151,8 @@ Compute Unit(s) : NPU (659 ops)
|
|
153 |
CLIPTextEncoder
|
154 |
Device : Samsung Galaxy S23 (13)
|
155 |
Runtime : TFLITE
|
156 |
-
Estimated inference time (ms) : 5.
|
157 |
-
Estimated peak memory usage (MB): [0,
|
158 |
Total # Ops : 660
|
159 |
Compute Unit(s) : NPU (658 ops) CPU (2 ops)
|
160 |
```
|
@@ -287,7 +285,8 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
|
|
287 |
|
288 |
|
289 |
## License
|
290 |
-
* The license for the original implementation of OpenAI-Clip can be found
|
|
|
291 |
* The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)
|
292 |
|
293 |
|
|
|
38 |
|
39 |
| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
40 |
|---|---|---|---|---|---|---|---|---|
|
41 |
+
| CLIPImageEncoder | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 34.319 ms | 0 - 54 MB | FP16 | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPImageEncoder.tflite) |
|
42 |
+
| CLIPImageEncoder | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 26.337 ms | 0 - 56 MB | FP16 | NPU | [OpenAI-Clip.so](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPImageEncoder.so) |
|
43 |
+
| CLIPImageEncoder | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 27.11 ms | 0 - 265 MB | FP16 | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPImageEncoder.tflite) |
|
44 |
+
| CLIPImageEncoder | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 20.295 ms | 0 - 172 MB | FP16 | NPU | [OpenAI-Clip.so](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPImageEncoder.so) |
|
45 |
+
| CLIPImageEncoder | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 25.123 ms | 0 - 265 MB | FP16 | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPImageEncoder.tflite) |
|
46 |
+
| CLIPImageEncoder | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 16.937 ms | 1 - 173 MB | FP16 | NPU | Use Export Script |
|
47 |
+
| CLIPImageEncoder | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 34.064 ms | 0 - 63 MB | FP16 | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPImageEncoder.tflite) |
|
48 |
+
| CLIPImageEncoder | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 20.375 ms | 1 - 4 MB | FP16 | NPU | Use Export Script |
|
49 |
+
| CLIPImageEncoder | SA7255P ADP | SA7255P | TFLITE | 326.663 ms | 0 - 264 MB | FP16 | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPImageEncoder.tflite) |
|
50 |
+
| CLIPImageEncoder | SA7255P ADP | SA7255P | QNN | 264.763 ms | 1 - 9 MB | FP16 | NPU | Use Export Script |
|
51 |
+
| CLIPImageEncoder | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 34.194 ms | 0 - 56 MB | FP16 | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPImageEncoder.tflite) |
|
52 |
+
| CLIPImageEncoder | SA8255 (Proxy) | SA8255P Proxy | QNN | 20.535 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
|
53 |
+
| CLIPImageEncoder | SA8295P ADP | SA8295P | TFLITE | 40.104 ms | 0 - 202 MB | FP16 | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPImageEncoder.tflite) |
|
54 |
+
| CLIPImageEncoder | SA8295P ADP | SA8295P | QNN | 30.975 ms | 1 - 15 MB | FP16 | NPU | Use Export Script |
|
55 |
+
| CLIPImageEncoder | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 34.131 ms | 0 - 50 MB | FP16 | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPImageEncoder.tflite) |
|
56 |
+
| CLIPImageEncoder | SA8650 (Proxy) | SA8650P Proxy | QNN | 20.714 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
|
57 |
+
| CLIPImageEncoder | SA8775P ADP | SA8775P | TFLITE | 42.575 ms | 0 - 264 MB | FP16 | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPImageEncoder.tflite) |
|
58 |
+
| CLIPImageEncoder | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 35.825 ms | 0 - 202 MB | FP16 | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPImageEncoder.tflite) |
|
59 |
+
| CLIPImageEncoder | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 29.758 ms | 0 - 166 MB | FP16 | NPU | Use Export Script |
|
60 |
+
| CLIPImageEncoder | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 22.195 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
|
61 |
+
| CLIPTextEncoder | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 5.68 ms | 0 - 24 MB | FP16 | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPTextEncoder.tflite) |
|
62 |
+
| CLIPTextEncoder | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 4.678 ms | 0 - 25 MB | FP16 | NPU | [OpenAI-Clip.so](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPTextEncoder.so) |
|
63 |
+
| CLIPTextEncoder | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 3.993 ms | 0 - 88 MB | FP16 | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPTextEncoder.tflite) |
|
64 |
+
| CLIPTextEncoder | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 3.297 ms | 0 - 71 MB | FP16 | NPU | [OpenAI-Clip.so](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPTextEncoder.so) |
|
65 |
+
| CLIPTextEncoder | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 3.98 ms | 0 - 85 MB | FP16 | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPTextEncoder.tflite) |
|
66 |
+
| CLIPTextEncoder | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 3.232 ms | 0 - 70 MB | FP16 | NPU | Use Export Script |
|
67 |
+
| CLIPTextEncoder | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 5.699 ms | 0 - 18 MB | FP16 | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPTextEncoder.tflite) |
|
68 |
+
| CLIPTextEncoder | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 4.768 ms | 0 - 3 MB | FP16 | NPU | Use Export Script |
|
69 |
+
| CLIPTextEncoder | SA7255P ADP | SA7255P | TFLITE | 61.254 ms | 0 - 81 MB | FP16 | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPTextEncoder.tflite) |
|
70 |
+
| CLIPTextEncoder | SA7255P ADP | SA7255P | QNN | 51.477 ms | 0 - 9 MB | FP16 | NPU | Use Export Script |
|
71 |
+
| CLIPTextEncoder | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 5.722 ms | 0 - 24 MB | FP16 | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPTextEncoder.tflite) |
|
72 |
+
| CLIPTextEncoder | SA8255 (Proxy) | SA8255P Proxy | QNN | 4.804 ms | 0 - 2 MB | FP16 | NPU | Use Export Script |
|
73 |
+
| CLIPTextEncoder | SA8295P ADP | SA8295P | TFLITE | 7.627 ms | 0 - 69 MB | FP16 | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPTextEncoder.tflite) |
|
74 |
+
| CLIPTextEncoder | SA8295P ADP | SA8295P | QNN | 6.596 ms | 0 - 14 MB | FP16 | NPU | Use Export Script |
|
75 |
+
| CLIPTextEncoder | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 5.726 ms | 0 - 18 MB | FP16 | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPTextEncoder.tflite) |
|
76 |
+
| CLIPTextEncoder | SA8650 (Proxy) | SA8650P Proxy | QNN | 4.811 ms | 0 - 3 MB | FP16 | NPU | Use Export Script |
|
77 |
+
| CLIPTextEncoder | SA8775P ADP | SA8775P | TFLITE | 8.166 ms | 0 - 81 MB | FP16 | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPTextEncoder.tflite) |
|
78 |
+
| CLIPTextEncoder | SA8775P ADP | SA8775P | QNN | 6.929 ms | 0 - 10 MB | FP16 | NPU | Use Export Script |
|
79 |
+
| CLIPTextEncoder | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 6.336 ms | 0 - 74 MB | FP16 | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPTextEncoder.tflite) |
|
80 |
+
| CLIPTextEncoder | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 5.216 ms | 0 - 71 MB | FP16 | NPU | Use Export Script |
|
81 |
+
| CLIPTextEncoder | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 5.104 ms | 0 - 0 MB | FP16 | NPU | Use Export Script |
|
|
|
82 |
|
83 |
|
84 |
|
85 |
|
86 |
## Installation
|
87 |
|
|
|
88 |
|
89 |
+
Install the package via pip:
|
90 |
```bash
|
91 |
+
pip install "qai-hub-models[openai-clip]"
|
92 |
```
|
93 |
|
94 |
|
|
|
95 |
## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
|
96 |
|
97 |
Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
|
|
|
142 |
CLIPImageEncoder
|
143 |
Device : Samsung Galaxy S23 (13)
|
144 |
Runtime : TFLITE
|
145 |
+
Estimated inference time (ms) : 34.3
|
146 |
+
Estimated peak memory usage (MB): [0, 54]
|
147 |
Total # Ops : 659
|
148 |
Compute Unit(s) : NPU (659 ops)
|
149 |
|
|
|
151 |
CLIPTextEncoder
|
152 |
Device : Samsung Galaxy S23 (13)
|
153 |
Runtime : TFLITE
|
154 |
+
Estimated inference time (ms) : 5.7
|
155 |
+
Estimated peak memory usage (MB): [0, 24]
|
156 |
Total # Ops : 660
|
157 |
Compute Unit(s) : NPU (658 ops) CPU (2 ops)
|
158 |
```
|
|
|
285 |
|
286 |
|
287 |
## License
|
288 |
+
* The license for the original implementation of OpenAI-Clip can be found
|
289 |
+
[here](https://github.com/openai/CLIP/blob/main/LICENSE).
|
290 |
* The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)
|
291 |
|
292 |
|