Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -37,8 +37,8 @@ More details on model performance across various devices, can be found
|
|
37 |
|
38 |
| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
39 |
| ---|---|---|---|---|---|---|---|
|
40 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 1.
|
41 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 1.
|
42 |
|
43 |
|
44 |
## Installation
|
@@ -95,23 +95,6 @@ device. This script does the following:
|
|
95 |
python -m qai_hub_models.models.resnet101_quantized.export
|
96 |
```
|
97 |
|
98 |
-
```
|
99 |
-
Profile Job summary of ResNet101Quantized
|
100 |
-
--------------------------------------------------
|
101 |
-
Device: Samsung Galaxy S24 (14)
|
102 |
-
Estimated Inference Time: 0.86 ms
|
103 |
-
Estimated Peak Memory Range: 0.02-87.90 MB
|
104 |
-
Compute Units: NPU (146) | Total (146)
|
105 |
-
|
106 |
-
Profile Job summary of ResNet101Quantized
|
107 |
-
--------------------------------------------------
|
108 |
-
Device: Samsung Galaxy S24 (14)
|
109 |
-
Estimated Inference Time: 0.82 ms
|
110 |
-
Estimated Peak Memory Range: 0.16-51.42 MB
|
111 |
-
Compute Units: NPU (143) | Total (143)
|
112 |
-
|
113 |
-
|
114 |
-
```
|
115 |
## How does this work?
|
116 |
|
117 |
This [export script](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/ResNet101Quantized/export.py)
|
|
|
37 |
|
38 |
| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
39 |
| ---|---|---|---|---|---|---|---|
|
40 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 1.171 ms | 0 - 2 MB | INT8 | NPU | [ResNet101Quantized.tflite](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.tflite)
|
41 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 1.394 ms | 0 - 178 MB | INT8 | NPU | [ResNet101Quantized.so](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.so)
|
42 |
|
43 |
|
44 |
## Installation
|
|
|
95 |
python -m qai_hub_models.models.resnet101_quantized.export
|
96 |
```
|
97 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
98 |
## How does this work?
|
99 |
|
100 |
This [export script](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/ResNet101Quantized/export.py)
|