Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -34,8 +34,8 @@ More details on model performance across various devices, can be found
|
|
34 |
|
35 |
| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
36 |
| ---|---|---|---|---|---|---|---|
|
37 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 3.
|
38 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 3.
|
39 |
|
40 |
|
41 |
|
@@ -99,8 +99,8 @@ Profile Job summary of Midas-V2
|
|
99 |
--------------------------------------------------
|
100 |
Device: SA8255 (Proxy) (13)
|
101 |
Estimated Inference Time: 3.38 ms
|
102 |
-
Estimated Peak Memory Range: 0.77-
|
103 |
-
Compute Units: NPU (
|
104 |
|
105 |
|
106 |
```
|
|
|
34 |
|
35 |
| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
36 |
| ---|---|---|---|---|---|---|---|
|
37 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 3.43 ms | 0 - 2 MB | FP16 | NPU | [Midas-V2.tflite](https://huggingface.co/qualcomm/Midas-V2/blob/main/Midas-V2.tflite)
|
38 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 3.398 ms | 1 - 18 MB | FP16 | NPU | [Midas-V2.so](https://huggingface.co/qualcomm/Midas-V2/blob/main/Midas-V2.so)
|
39 |
|
40 |
|
41 |
|
|
|
99 |
--------------------------------------------------
|
100 |
Device: SA8255 (Proxy) (13)
|
101 |
Estimated Inference Time: 3.38 ms
|
102 |
+
Estimated Peak Memory Range: 0.77-16.00 MB
|
103 |
+
Compute Units: NPU (198) | Total (198)
|
104 |
|
105 |
|
106 |
```
|