Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -33,7 +33,7 @@ More details on model performance across various devices, can be found
|
|
| 33 |
|
| 34 |
| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
| 35 |
| ---|---|---|---|---|---|---|---|
|
| 36 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite |
|
| 37 |
|
| 38 |
|
| 39 |
## Installation
|
|
@@ -91,16 +91,6 @@ device. This script does the following:
|
|
| 91 |
python -m qai_hub_models.models.yolov7.export
|
| 92 |
```
|
| 93 |
|
| 94 |
-
```
|
| 95 |
-
Profile Job summary of Yolo-v7
|
| 96 |
-
--------------------------------------------------
|
| 97 |
-
Device: Samsung Galaxy S24 (14)
|
| 98 |
-
Estimated Inference Time: 19.40 ms
|
| 99 |
-
Estimated Peak Memory Range: 0.01-125.41 MB
|
| 100 |
-
Compute Units: NPU (286),CPU (21) | Total (307)
|
| 101 |
-
|
| 102 |
-
|
| 103 |
-
```
|
| 104 |
## How does this work?
|
| 105 |
|
| 106 |
This [export script](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/Yolo-v7/export.py)
|
|
|
|
| 33 |
|
| 34 |
| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
| 35 |
| ---|---|---|---|---|---|---|---|
|
| 36 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 20.875 ms | 9 - 43 MB | FP16 | NPU | [Yolo-v7.tflite](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.tflite)
|
| 37 |
|
| 38 |
|
| 39 |
## Installation
|
|
|
|
| 91 |
python -m qai_hub_models.models.yolov7.export
|
| 92 |
```
|
| 93 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 94 |
## How does this work?
|
| 95 |
|
| 96 |
This [export script](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/Yolo-v7/export.py)
|