Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -36,7 +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 | 4.
|
|
|
40 |
|
41 |
|
42 |
|
@@ -98,10 +99,10 @@ python -m qai_hub_models.models.yolov7_quantized.export
|
|
98 |
```
|
99 |
Profile Job summary of Yolo-v7-Quantized
|
100 |
--------------------------------------------------
|
101 |
-
Device:
|
102 |
-
Estimated Inference Time:
|
103 |
-
Estimated Peak Memory Range:
|
104 |
-
Compute Units: NPU (
|
105 |
|
106 |
|
107 |
```
|
|
|
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 | 4.43 ms | 0 - 143 MB | INT8 | NPU | [Yolo-v7-Quantized.tflite](https://huggingface.co/qualcomm/Yolo-v7-Quantized/blob/main/Yolo-v7-Quantized.tflite)
|
40 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 4.818 ms | 0 - 10 MB | INT8 | NPU | Yolo-v7-Quantized
|
41 |
|
42 |
|
43 |
|
|
|
99 |
```
|
100 |
Profile Job summary of Yolo-v7-Quantized
|
101 |
--------------------------------------------------
|
102 |
+
Device: Snapdragon X Elite CRD (11)
|
103 |
+
Estimated Inference Time: 3.88 ms
|
104 |
+
Estimated Peak Memory Range: 1.18-1.18 MB
|
105 |
+
Compute Units: NPU (221) | Total (221)
|
106 |
|
107 |
|
108 |
```
|