Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -36,7 +36,7 @@ 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 | 7.
|
40 |
|
41 |
|
42 |
## Installation
|
@@ -94,16 +94,6 @@ device. This script does the following:
|
|
94 |
python -m qai_hub_models.models.ffnet_54s_quantized.export
|
95 |
```
|
96 |
|
97 |
-
```
|
98 |
-
Profile Job summary of FFNet-54S-Quantized
|
99 |
-
--------------------------------------------------
|
100 |
-
Device: Samsung Galaxy S24 (14)
|
101 |
-
Estimated Inference Time: 5.15 ms
|
102 |
-
Estimated Peak Memory Range: 0.22-71.35 MB
|
103 |
-
Compute Units: NPU (118) | Total (118)
|
104 |
-
|
105 |
-
|
106 |
-
```
|
107 |
## How does this work?
|
108 |
|
109 |
This [export script](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/FFNet-54S-Quantized/export.py)
|
|
|
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 | 7.125 ms | 1 - 2 MB | INT8 | NPU | [FFNet-54S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-54S-Quantized/blob/main/FFNet-54S-Quantized.tflite)
|
40 |
|
41 |
|
42 |
## Installation
|
|
|
94 |
python -m qai_hub_models.models.ffnet_54s_quantized.export
|
95 |
```
|
96 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
97 |
## How does this work?
|
98 |
|
99 |
This [export script](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/FFNet-54S-Quantized/export.py)
|