Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -34,45 +34,44 @@ More details on model performance across various devices, can be found
|
|
34 |
|
35 |
| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
36 |
|---|---|---|---|---|---|---|---|---|
|
37 |
-
| DETR-ResNet50 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 10.
|
38 |
-
| DETR-ResNet50 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 11.
|
39 |
-
| DETR-ResNet50 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX |
|
40 |
-
| DETR-ResNet50 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 7.739 ms | 0 -
|
41 |
-
| DETR-ResNet50 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 8.
|
42 |
-
| DETR-ResNet50 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 8.
|
43 |
-
| DETR-ResNet50 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 7.
|
44 |
-
| DETR-ResNet50 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 8.
|
45 |
-
| DETR-ResNet50 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX |
|
46 |
-
| DETR-ResNet50 | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 10.
|
47 |
-
| DETR-ResNet50 | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 10.
|
48 |
-
| DETR-ResNet50 | SA7255P ADP | SA7255P | TFLITE | 309.
|
49 |
-
| DETR-ResNet50 | SA7255P ADP | SA7255P | QNN | 310.
|
50 |
-
| DETR-ResNet50 | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 10.
|
51 |
-
| DETR-ResNet50 | SA8255 (Proxy) | SA8255P Proxy | QNN | 10.
|
52 |
-
| DETR-ResNet50 | SA8295P ADP | SA8295P | TFLITE | 16.
|
53 |
-
| DETR-ResNet50 | SA8295P ADP | SA8295P | QNN | 17.
|
54 |
-
| DETR-ResNet50 | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 10.
|
55 |
-
| DETR-ResNet50 | SA8650 (Proxy) | SA8650P Proxy | QNN | 10.
|
56 |
-
| DETR-ResNet50 | SA8775P ADP | SA8775P | TFLITE | 18.
|
57 |
-
| DETR-ResNet50 | SA8775P ADP | SA8775P | QNN | 17.
|
58 |
-
| DETR-ResNet50 | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 14.
|
59 |
-
| DETR-ResNet50 | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 15.
|
60 |
-
| DETR-ResNet50 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN |
|
61 |
-
| DETR-ResNet50 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 13.
|
62 |
|
63 |
|
64 |
|
65 |
|
66 |
## Installation
|
67 |
|
68 |
-
This model can be installed as a Python package via pip.
|
69 |
|
|
|
70 |
```bash
|
71 |
-
pip install "qai-hub-models[
|
72 |
```
|
73 |
|
74 |
|
75 |
-
|
76 |
## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
|
77 |
|
78 |
Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
|
@@ -151,7 +150,7 @@ from qai_hub_models.models.detr_resnet50 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 +242,8 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
|
|
243 |
|
244 |
|
245 |
## License
|
246 |
-
* The license for the original implementation of DETR-ResNet50 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 |
|
|
|
34 |
|
35 |
| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
36 |
|---|---|---|---|---|---|---|---|---|
|
37 |
+
| DETR-ResNet50 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 10.838 ms | 0 - 20 MB | FP16 | NPU | [DETR-ResNet50.tflite](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.tflite) |
|
38 |
+
| DETR-ResNet50 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 11.896 ms | 3 - 21 MB | FP16 | NPU | [DETR-ResNet50.so](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.so) |
|
39 |
+
| DETR-ResNet50 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 12.067 ms | 1 - 238 MB | FP16 | NPU | [DETR-ResNet50.onnx](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.onnx) |
|
40 |
+
| DETR-ResNet50 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 7.739 ms | 0 - 64 MB | FP16 | NPU | [DETR-ResNet50.tflite](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.tflite) |
|
41 |
+
| DETR-ResNet50 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 8.454 ms | 3 - 68 MB | FP16 | NPU | [DETR-ResNet50.so](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.so) |
|
42 |
+
| DETR-ResNet50 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 8.582 ms | 3 - 89 MB | FP16 | NPU | [DETR-ResNet50.onnx](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.onnx) |
|
43 |
+
| DETR-ResNet50 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 7.247 ms | 0 - 66 MB | FP16 | NPU | [DETR-ResNet50.tflite](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.tflite) |
|
44 |
+
| DETR-ResNet50 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 8.042 ms | 3 - 70 MB | FP16 | NPU | Use Export Script |
|
45 |
+
| DETR-ResNet50 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 7.064 ms | 3 - 64 MB | FP16 | NPU | [DETR-ResNet50.onnx](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.onnx) |
|
46 |
+
| DETR-ResNet50 | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 10.793 ms | 0 - 31 MB | FP16 | NPU | [DETR-ResNet50.tflite](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.tflite) |
|
47 |
+
| DETR-ResNet50 | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 10.439 ms | 3 - 5 MB | FP16 | NPU | Use Export Script |
|
48 |
+
| DETR-ResNet50 | SA7255P ADP | SA7255P | TFLITE | 309.001 ms | 0 - 65 MB | FP16 | NPU | [DETR-ResNet50.tflite](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.tflite) |
|
49 |
+
| DETR-ResNet50 | SA7255P ADP | SA7255P | QNN | 310.452 ms | 2 - 11 MB | FP16 | NPU | Use Export Script |
|
50 |
+
| DETR-ResNet50 | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 10.76 ms | 0 - 27 MB | FP16 | NPU | [DETR-ResNet50.tflite](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.tflite) |
|
51 |
+
| DETR-ResNet50 | SA8255 (Proxy) | SA8255P Proxy | QNN | 10.612 ms | 3 - 5 MB | FP16 | NPU | Use Export Script |
|
52 |
+
| DETR-ResNet50 | SA8295P ADP | SA8295P | TFLITE | 16.387 ms | 0 - 49 MB | FP16 | NPU | [DETR-ResNet50.tflite](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.tflite) |
|
53 |
+
| DETR-ResNet50 | SA8295P ADP | SA8295P | QNN | 17.075 ms | 0 - 14 MB | FP16 | NPU | Use Export Script |
|
54 |
+
| DETR-ResNet50 | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 10.858 ms | 0 - 25 MB | FP16 | NPU | [DETR-ResNet50.tflite](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.tflite) |
|
55 |
+
| DETR-ResNet50 | SA8650 (Proxy) | SA8650P Proxy | QNN | 10.495 ms | 3 - 5 MB | FP16 | NPU | Use Export Script |
|
56 |
+
| DETR-ResNet50 | SA8775P ADP | SA8775P | TFLITE | 18.381 ms | 0 - 62 MB | FP16 | NPU | [DETR-ResNet50.tflite](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.tflite) |
|
57 |
+
| DETR-ResNet50 | SA8775P ADP | SA8775P | QNN | 17.918 ms | 1 - 11 MB | FP16 | NPU | Use Export Script |
|
58 |
+
| DETR-ResNet50 | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 14.332 ms | 0 - 49 MB | FP16 | NPU | [DETR-ResNet50.tflite](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.tflite) |
|
59 |
+
| DETR-ResNet50 | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 15.24 ms | 3 - 48 MB | FP16 | NPU | Use Export Script |
|
60 |
+
| DETR-ResNet50 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 10.78 ms | 3 - 3 MB | FP16 | NPU | Use Export Script |
|
61 |
+
| DETR-ResNet50 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 13.158 ms | 80 - 80 MB | FP16 | NPU | [DETR-ResNet50.onnx](https://huggingface.co/qualcomm/DETR-ResNet50/blob/main/DETR-ResNet50.onnx) |
|
62 |
|
63 |
|
64 |
|
65 |
|
66 |
## Installation
|
67 |
|
|
|
68 |
|
69 |
+
Install the package via pip:
|
70 |
```bash
|
71 |
+
pip install "qai-hub-models[detr-resnet50]"
|
72 |
```
|
73 |
|
74 |
|
|
|
75 |
## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
|
76 |
|
77 |
Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
|
|
|
150 |
torch_model = Model.from_pretrained()
|
151 |
|
152 |
# Device
|
153 |
+
device = hub.Device("Samsung Galaxy S24")
|
154 |
|
155 |
# Trace model
|
156 |
input_shape = torch_model.get_input_spec()
|
|
|
242 |
|
243 |
|
244 |
## License
|
245 |
+
* The license for the original implementation of DETR-ResNet50 can be found
|
246 |
+
[here](https://github.com/facebookresearch/detr/blob/main/LICENSE).
|
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 |
|