Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -35,39 +35,39 @@ More details on model performance across various devices, can be found
|
|
| 35 |
|
| 36 |
| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
| 37 |
|---|---|---|---|---|---|---|---|---|
|
| 38 |
-
| RegNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 2.
|
| 39 |
-
| RegNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 2.
|
| 40 |
-
| RegNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 2.
|
| 41 |
-
| RegNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 1.
|
| 42 |
-
| RegNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 1.
|
| 43 |
-
| RegNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 1.
|
| 44 |
-
| RegNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 1.
|
| 45 |
-
| RegNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 1.
|
| 46 |
-
| RegNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 1.
|
| 47 |
-
| RegNet | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 2.
|
| 48 |
-
| RegNet | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 2.
|
| 49 |
-
| RegNet | SA7255P ADP | SA7255P | TFLITE | 69.
|
| 50 |
-
| RegNet | SA7255P ADP | SA7255P | QNN | 69.
|
| 51 |
-
| RegNet | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 2.
|
| 52 |
-
| RegNet | SA8255 (Proxy) | SA8255P Proxy | QNN | 2.
|
| 53 |
-
| RegNet | SA8295P ADP | SA8295P | TFLITE | 3.
|
| 54 |
-
| RegNet | SA8295P ADP | SA8295P | QNN | 3.
|
| 55 |
-
| RegNet | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 2.
|
| 56 |
-
| RegNet | SA8650 (Proxy) | SA8650P Proxy | QNN | 2.
|
| 57 |
-
| RegNet | SA8775P ADP | SA8775P | TFLITE | 3.
|
| 58 |
-
| RegNet | SA8775P ADP | SA8775P | QNN | 4.
|
| 59 |
-
| RegNet | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 2.
|
| 60 |
-
| RegNet | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 2.
|
| 61 |
-
| RegNet | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 2.
|
| 62 |
-
| RegNet | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2.
|
| 63 |
|
| 64 |
|
| 65 |
|
| 66 |
|
| 67 |
## Installation
|
| 68 |
|
| 69 |
-
This model can be installed as a Python package via pip.
|
| 70 |
|
|
|
|
| 71 |
```bash
|
| 72 |
pip install qai-hub-models
|
| 73 |
```
|
|
@@ -124,7 +124,7 @@ RegNet
|
|
| 124 |
Device : Samsung Galaxy S23 (13)
|
| 125 |
Runtime : TFLITE
|
| 126 |
Estimated inference time (ms) : 2.0
|
| 127 |
-
Estimated peak memory usage (MB): [0,
|
| 128 |
Total # Ops : 114
|
| 129 |
Compute Unit(s) : NPU (114 ops)
|
| 130 |
```
|
|
@@ -151,7 +151,7 @@ from qai_hub_models.models.regnet import Model
|
|
| 151 |
torch_model = Model.from_pretrained()
|
| 152 |
|
| 153 |
# Device
|
| 154 |
-
device = hub.Device("Samsung Galaxy
|
| 155 |
|
| 156 |
# Trace model
|
| 157 |
input_shape = torch_model.get_input_spec()
|
|
@@ -243,7 +243,8 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
|
|
| 243 |
|
| 244 |
|
| 245 |
## License
|
| 246 |
-
* The license for the original implementation of RegNet can be found
|
|
|
|
| 247 |
* The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)
|
| 248 |
|
| 249 |
|
|
|
|
| 35 |
|
| 36 |
| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
| 37 |
|---|---|---|---|---|---|---|---|---|
|
| 38 |
+
| RegNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 2.038 ms | 0 - 113 MB | FP16 | NPU | [RegNet.tflite](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.tflite) |
|
| 39 |
+
| RegNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 2.138 ms | 0 - 70 MB | FP16 | NPU | [RegNet.so](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.so) |
|
| 40 |
+
| RegNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 2.178 ms | 0 - 74 MB | FP16 | NPU | [RegNet.onnx](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.onnx) |
|
| 41 |
+
| RegNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 1.396 ms | 0 - 33 MB | FP16 | NPU | [RegNet.tflite](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.tflite) |
|
| 42 |
+
| RegNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 1.477 ms | 1 - 33 MB | FP16 | NPU | [RegNet.so](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.so) |
|
| 43 |
+
| RegNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 1.546 ms | 0 - 35 MB | FP16 | NPU | [RegNet.onnx](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.onnx) |
|
| 44 |
+
| RegNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 1.368 ms | 0 - 32 MB | FP16 | NPU | [RegNet.tflite](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.tflite) |
|
| 45 |
+
| RegNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 1.204 ms | 1 - 32 MB | FP16 | NPU | Use Export Script |
|
| 46 |
+
| RegNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 1.575 ms | 1 - 34 MB | FP16 | NPU | [RegNet.onnx](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.onnx) |
|
| 47 |
+
| RegNet | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 2.014 ms | 0 - 122 MB | FP16 | NPU | [RegNet.tflite](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.tflite) |
|
| 48 |
+
| RegNet | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 2.023 ms | 1 - 4 MB | FP16 | NPU | Use Export Script |
|
| 49 |
+
| RegNet | SA7255P ADP | SA7255P | TFLITE | 69.186 ms | 0 - 26 MB | FP16 | NPU | [RegNet.tflite](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.tflite) |
|
| 50 |
+
| RegNet | SA7255P ADP | SA7255P | QNN | 69.608 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
|
| 51 |
+
| RegNet | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 2.027 ms | 0 - 112 MB | FP16 | NPU | [RegNet.tflite](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.tflite) |
|
| 52 |
+
| RegNet | SA8255 (Proxy) | SA8255P Proxy | QNN | 2.02 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
|
| 53 |
+
| RegNet | SA8295P ADP | SA8295P | TFLITE | 3.556 ms | 0 - 26 MB | FP16 | NPU | [RegNet.tflite](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.tflite) |
|
| 54 |
+
| RegNet | SA8295P ADP | SA8295P | QNN | 3.646 ms | 0 - 14 MB | FP16 | NPU | Use Export Script |
|
| 55 |
+
| RegNet | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 2.048 ms | 0 - 112 MB | FP16 | NPU | [RegNet.tflite](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.tflite) |
|
| 56 |
+
| RegNet | SA8650 (Proxy) | SA8650P Proxy | QNN | 2.039 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
|
| 57 |
+
| RegNet | SA8775P ADP | SA8775P | TFLITE | 3.931 ms | 0 - 27 MB | FP16 | NPU | [RegNet.tflite](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.tflite) |
|
| 58 |
+
| RegNet | SA8775P ADP | SA8775P | QNN | 4.153 ms | 1 - 11 MB | FP16 | NPU | Use Export Script |
|
| 59 |
+
| RegNet | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 2.804 ms | 0 - 31 MB | FP16 | NPU | [RegNet.tflite](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.tflite) |
|
| 60 |
+
| RegNet | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 2.912 ms | 1 - 24 MB | FP16 | NPU | Use Export Script |
|
| 61 |
+
| RegNet | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 2.201 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
|
| 62 |
+
| RegNet | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2.233 ms | 41 - 41 MB | FP16 | NPU | [RegNet.onnx](https://huggingface.co/qualcomm/RegNet/blob/main/RegNet.onnx) |
|
| 63 |
|
| 64 |
|
| 65 |
|
| 66 |
|
| 67 |
## Installation
|
| 68 |
|
|
|
|
| 69 |
|
| 70 |
+
Install the package via pip:
|
| 71 |
```bash
|
| 72 |
pip install qai-hub-models
|
| 73 |
```
|
|
|
|
| 124 |
Device : Samsung Galaxy S23 (13)
|
| 125 |
Runtime : TFLITE
|
| 126 |
Estimated inference time (ms) : 2.0
|
| 127 |
+
Estimated peak memory usage (MB): [0, 113]
|
| 128 |
Total # Ops : 114
|
| 129 |
Compute Unit(s) : NPU (114 ops)
|
| 130 |
```
|
|
|
|
| 151 |
torch_model = Model.from_pretrained()
|
| 152 |
|
| 153 |
# Device
|
| 154 |
+
device = hub.Device("Samsung Galaxy S24")
|
| 155 |
|
| 156 |
# Trace model
|
| 157 |
input_shape = torch_model.get_input_spec()
|
|
|
|
| 243 |
|
| 244 |
|
| 245 |
## License
|
| 246 |
+
* The license for the original implementation of RegNet can be found
|
| 247 |
+
[here](https://github.com/pytorch/vision/blob/main/LICENSE).
|
| 248 |
* The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)
|
| 249 |
|
| 250 |
|