Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -93,6 +93,23 @@ device. This script does the following:
|
|
| 93 |
python -m qai_hub_models.models.ffnet_122ns_lowres.export
|
| 94 |
```
|
| 95 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 96 |
## How does this work?
|
| 97 |
|
| 98 |
This [export script](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/FFNet-122NS-LowRes/export.py)
|
|
|
|
| 93 |
python -m qai_hub_models.models.ffnet_122ns_lowres.export
|
| 94 |
```
|
| 95 |
|
| 96 |
+
```
|
| 97 |
+
Profile Job summary of FFNet-122NS-LowRes
|
| 98 |
+
--------------------------------------------------
|
| 99 |
+
Device: QCS8550 (Proxy) (12)
|
| 100 |
+
Estimated Inference Time: 9.66 ms
|
| 101 |
+
Estimated Peak Memory Range: 0.00-3.85 MB
|
| 102 |
+
Compute Units: NPU (216) | Total (216)
|
| 103 |
+
|
| 104 |
+
Profile Job summary of FFNet-122NS-LowRes
|
| 105 |
+
--------------------------------------------------
|
| 106 |
+
Device: QCS8550 (Proxy) (12)
|
| 107 |
+
Estimated Inference Time: 10.82 ms
|
| 108 |
+
Estimated Peak Memory Range: 6.04-36.75 MB
|
| 109 |
+
Compute Units: NPU (348) | Total (348)
|
| 110 |
+
|
| 111 |
+
|
| 112 |
+
```
|
| 113 |
## How does this work?
|
| 114 |
|
| 115 |
This [export script](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/FFNet-122NS-LowRes/export.py)
|