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 | 1.088 ms | 0 -
|
42 |
|
43 |
|
44 |
|
@@ -100,7 +100,7 @@ python -m qai_hub_models.models.googlenet.export
|
|
100 |
Profile Job summary of GoogLeNet
|
101 |
--------------------------------------------------
|
102 |
Device: Snapdragon X Elite CRD (11)
|
103 |
-
Estimated Inference Time: 1.
|
104 |
Estimated Peak Memory Range: 0.57-0.57 MB
|
105 |
Compute Units: NPU (143) | Total (143)
|
106 |
|
@@ -127,7 +127,6 @@ from qai_hub_models.models.googlenet import Model
|
|
127 |
|
128 |
# Load the model
|
129 |
torch_model = Model.from_pretrained()
|
130 |
-
torch_model.eval()
|
131 |
|
132 |
# Device
|
133 |
device = hub.Device("Samsung Galaxy S23")
|
|
|
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 | 1.046 ms | 0 - 2 MB | FP16 | NPU | [GoogLeNet.tflite](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.tflite)
|
41 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 1.088 ms | 0 - 87 MB | FP16 | NPU | [GoogLeNet.so](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.so)
|
42 |
|
43 |
|
44 |
|
|
|
100 |
Profile Job summary of GoogLeNet
|
101 |
--------------------------------------------------
|
102 |
Device: Snapdragon X Elite CRD (11)
|
103 |
+
Estimated Inference Time: 1.23 ms
|
104 |
Estimated Peak Memory Range: 0.57-0.57 MB
|
105 |
Compute Units: NPU (143) | Total (143)
|
106 |
|
|
|
127 |
|
128 |
# Load the model
|
129 |
torch_model = Model.from_pretrained()
|
|
|
130 |
|
131 |
# Device
|
132 |
device = hub.Device("Samsung Galaxy S23")
|