Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -36,10 +36,8 @@ More details on model performance across various devices, can be found
|
|
| 36 |
|
| 37 |
| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
| 38 |
| ---|---|---|---|---|---|---|---|
|
| 39 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 15.
|
| 40 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 126.
|
| 41 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 8.102 ms | 0 - 20 MB | FP16 | NPU | [CLIPTextEncoder.so](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPTextEncoder.so)
|
| 42 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 50.465 ms | 0 - 59 MB | FP16 | NPU | [CLIPImageEncoder.so](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPImageEncoder.so)
|
| 43 |
|
| 44 |
|
| 45 |
## Installation
|
|
@@ -97,37 +95,6 @@ device. This script does the following:
|
|
| 97 |
python -m qai_hub_models.models.openai_clip.export
|
| 98 |
```
|
| 99 |
|
| 100 |
-
```
|
| 101 |
-
Profile Job summary of CLIPTextEncoder
|
| 102 |
-
--------------------------------------------------
|
| 103 |
-
Device: Samsung Galaxy S24 (14)
|
| 104 |
-
Estimated Inference Time: 11.18 ms
|
| 105 |
-
Estimated Peak Memory Range: 0.02-210.88 MB
|
| 106 |
-
Compute Units: NPU (574),CPU (2) | Total (576)
|
| 107 |
-
|
| 108 |
-
Profile Job summary of CLIPImageEncoder
|
| 109 |
-
--------------------------------------------------
|
| 110 |
-
Device: Samsung Galaxy S24 (14)
|
| 111 |
-
Estimated Inference Time: 96.47 ms
|
| 112 |
-
Estimated Peak Memory Range: 0.25-827.19 MB
|
| 113 |
-
Compute Units: NPU (576) | Total (576)
|
| 114 |
-
|
| 115 |
-
Profile Job summary of CLIPTextEncoder
|
| 116 |
-
--------------------------------------------------
|
| 117 |
-
Device: Samsung Galaxy S24 (14)
|
| 118 |
-
Estimated Inference Time: 5.70 ms
|
| 119 |
-
Estimated Peak Memory Range: 0.01-136.97 MB
|
| 120 |
-
Compute Units: NPU (377) | Total (377)
|
| 121 |
-
|
| 122 |
-
Profile Job summary of CLIPImageEncoder
|
| 123 |
-
--------------------------------------------------
|
| 124 |
-
Device: Samsung Galaxy S24 (14)
|
| 125 |
-
Estimated Inference Time: 38.29 ms
|
| 126 |
-
Estimated Peak Memory Range: 0.61-217.84 MB
|
| 127 |
-
Compute Units: NPU (371) | Total (371)
|
| 128 |
-
|
| 129 |
-
|
| 130 |
-
```
|
| 131 |
## How does this work?
|
| 132 |
|
| 133 |
This [export script](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/OpenAI-Clip/export.py)
|
|
|
|
| 36 |
|
| 37 |
| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
| 38 |
| ---|---|---|---|---|---|---|---|
|
| 39 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 15.395 ms | 0 - 3 MB | FP16 | NPU | [CLIPTextEncoder.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPTextEncoder.tflite)
|
| 40 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 126.657 ms | 0 - 3 MB | FP16 | NPU | [CLIPImageEncoder.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPImageEncoder.tflite)
|
|
|
|
|
|
|
| 41 |
|
| 42 |
|
| 43 |
## Installation
|
|
|
|
| 95 |
python -m qai_hub_models.models.openai_clip.export
|
| 96 |
```
|
| 97 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 98 |
## How does this work?
|
| 99 |
|
| 100 |
This [export script](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/OpenAI-Clip/export.py)
|