Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -36,8 +36,8 @@ 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 |
|
40 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library |
|
41 |
|
42 |
|
43 |
|
@@ -100,7 +100,7 @@ python -m qai_hub_models.models.ffnet_122ns_lowres.export
|
|
100 |
Profile Job summary of FFNet-122NS-LowRes
|
101 |
--------------------------------------------------
|
102 |
Device: Snapdragon X Elite CRD (11)
|
103 |
-
Estimated Inference Time:
|
104 |
Estimated Peak Memory Range: 6.01-6.01 MB
|
105 |
Compute Units: NPU (348) | Total (348)
|
106 |
|
@@ -127,7 +127,6 @@ from qai_hub_models.models.ffnet_122ns_lowres 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")
|
|
|
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 | 6.446 ms | 1 - 3 MB | FP16 | NPU | [FFNet-122NS-LowRes.tflite](https://huggingface.co/qualcomm/FFNet-122NS-LowRes/blob/main/FFNet-122NS-LowRes.tflite)
|
40 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 6.982 ms | 6 - 31 MB | FP16 | NPU | [FFNet-122NS-LowRes.so](https://huggingface.co/qualcomm/FFNet-122NS-LowRes/blob/main/FFNet-122NS-LowRes.so)
|
41 |
|
42 |
|
43 |
|
|
|
100 |
Profile Job summary of FFNet-122NS-LowRes
|
101 |
--------------------------------------------------
|
102 |
Device: Snapdragon X Elite CRD (11)
|
103 |
+
Estimated Inference Time: 6.31 ms
|
104 |
Estimated Peak Memory Range: 6.01-6.01 MB
|
105 |
Compute Units: NPU (348) | Total (348)
|
106 |
|
|
|
127 |
|
128 |
# Load the model
|
129 |
torch_model = Model.from_pretrained()
|
|
|
130 |
|
131 |
# Device
|
132 |
device = hub.Device("Samsung Galaxy S23")
|