Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -33,8 +33,8 @@ 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 | 8.
|
37 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 8.
|
38 |
|
39 |
|
40 |
## Installation
|
@@ -96,7 +96,7 @@ python -m qai_hub_models.models.fastsam_s.export
|
|
96 |
Profile Job summary of FastSam-S
|
97 |
--------------------------------------------------
|
98 |
Device: Snapdragon X Elite CRD (11)
|
99 |
-
Estimated Inference Time: 9.
|
100 |
Estimated Peak Memory Range: 4.71-4.71 MB
|
101 |
Compute Units: NPU (286) | Total (286)
|
102 |
|
|
|
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 | 8.641 ms | 8 - 10 MB | FP16 | NPU | [FastSam-S.tflite](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.tflite)
|
37 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 8.21 ms | 5 - 20 MB | FP16 | NPU | [FastSam-S.so](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.so)
|
38 |
|
39 |
|
40 |
## Installation
|
|
|
96 |
Profile Job summary of FastSam-S
|
97 |
--------------------------------------------------
|
98 |
Device: Snapdragon X Elite CRD (11)
|
99 |
+
Estimated Inference Time: 9.29 ms
|
100 |
Estimated Peak Memory Range: 4.71-4.71 MB
|
101 |
Compute Units: NPU (286) | Total (286)
|
102 |
|