Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -38,10 +38,10 @@ More details on model performance across various devices, can be found
|
|
38 |
|
39 |
| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
40 |
| ---|---|---|---|---|---|---|---|
|
41 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite |
|
42 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite |
|
43 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 7.
|
44 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 50.
|
45 |
|
46 |
|
47 |
|
@@ -104,16 +104,16 @@ python -m qai_hub_models.models.openai_clip.export
|
|
104 |
Profile Job summary of CLIPTextEncoder
|
105 |
--------------------------------------------------
|
106 |
Device: Snapdragon X Elite CRD (11)
|
107 |
-
Estimated Inference Time: 8.
|
108 |
Estimated Peak Memory Range: 0.15-0.15 MB
|
109 |
Compute Units: NPU (377) | Total (377)
|
110 |
|
111 |
Profile Job summary of CLIPImageEncoder
|
112 |
--------------------------------------------------
|
113 |
Device: Snapdragon X Elite CRD (11)
|
114 |
-
Estimated Inference Time:
|
115 |
Estimated Peak Memory Range: 0.57-0.57 MB
|
116 |
-
Compute Units: NPU (
|
117 |
|
118 |
|
119 |
```
|
@@ -138,7 +138,6 @@ from qai_hub_models.models.openai_clip import Model
|
|
138 |
|
139 |
# Load the model
|
140 |
torch_model = Model.from_pretrained()
|
141 |
-
torch_model.eval()
|
142 |
|
143 |
# Device
|
144 |
device = hub.Device("Samsung Galaxy S23")
|
|
|
38 |
|
39 |
| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
40 |
| ---|---|---|---|---|---|---|---|
|
41 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 10.955 ms | 0 - 3 MB | FP16 | NPU | [CLIPTextEncoder.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPTextEncoder.tflite)
|
42 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 66.863 ms | 0 - 3 MB | FP16 | NPU | [CLIPImageEncoder.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPImageEncoder.tflite)
|
43 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 7.761 ms | 0 - 17 MB | FP16 | NPU | [CLIPTextEncoder.so](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPTextEncoder.so)
|
44 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 50.137 ms | 0 - 63 MB | FP16 | NPU | [CLIPImageEncoder.so](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPImageEncoder.so)
|
45 |
|
46 |
|
47 |
|
|
|
104 |
Profile Job summary of CLIPTextEncoder
|
105 |
--------------------------------------------------
|
106 |
Device: Snapdragon X Elite CRD (11)
|
107 |
+
Estimated Inference Time: 8.25 ms
|
108 |
Estimated Peak Memory Range: 0.15-0.15 MB
|
109 |
Compute Units: NPU (377) | Total (377)
|
110 |
|
111 |
Profile Job summary of CLIPImageEncoder
|
112 |
--------------------------------------------------
|
113 |
Device: Snapdragon X Elite CRD (11)
|
114 |
+
Estimated Inference Time: 36.05 ms
|
115 |
Estimated Peak Memory Range: 0.57-0.57 MB
|
116 |
+
Compute Units: NPU (370) | Total (370)
|
117 |
|
118 |
|
119 |
```
|
|
|
138 |
|
139 |
# Load the model
|
140 |
torch_model = Model.from_pretrained()
|
|
|
141 |
|
142 |
# Device
|
143 |
device = hub.Device("Samsung Galaxy S23")
|