Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -32,13 +32,14 @@ More details on model performance across various devices, can be found
|
|
| 32 |
- Input resolution: 2048x1024
|
| 33 |
- Number of parameters: 13.9M
|
| 34 |
- Model size: 13.5 MB
|
|
|
|
| 35 |
|
| 36 |
|
| 37 |
|
| 38 |
|
| 39 |
| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
| 40 |
| ---|---|---|---|---|---|---|---|
|
| 41 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite |
|
| 42 |
|
| 43 |
|
| 44 |
|
|
@@ -97,16 +98,6 @@ device. This script does the following:
|
|
| 97 |
python -m qai_hub_models.models.ffnet_40s_quantized.export
|
| 98 |
```
|
| 99 |
|
| 100 |
-
```
|
| 101 |
-
Profile Job summary of FFNet-40S-Quantized
|
| 102 |
-
--------------------------------------------------
|
| 103 |
-
Device: RB5 (Proxy) (12)
|
| 104 |
-
Estimated Inference Time: 189.48 ms
|
| 105 |
-
Estimated Peak Memory Range: 0.77-2.75 MB
|
| 106 |
-
Compute Units: NPU (97) | Total (97)
|
| 107 |
-
|
| 108 |
-
|
| 109 |
-
```
|
| 110 |
|
| 111 |
|
| 112 |
|
|
|
|
| 32 |
- Input resolution: 2048x1024
|
| 33 |
- Number of parameters: 13.9M
|
| 34 |
- Model size: 13.5 MB
|
| 35 |
+
- Number of output classes: 19
|
| 36 |
|
| 37 |
|
| 38 |
|
| 39 |
|
| 40 |
| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
| 41 |
| ---|---|---|---|---|---|---|---|
|
| 42 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 4.09 ms | 1 - 9 MB | INT8 | NPU | [FFNet-40S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-40S-Quantized/blob/main/FFNet-40S-Quantized.tflite)
|
| 43 |
|
| 44 |
|
| 45 |
|
|
|
|
| 98 |
python -m qai_hub_models.models.ffnet_40s_quantized.export
|
| 99 |
```
|
| 100 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 101 |
|
| 102 |
|
| 103 |
|