Hugging Face's logo

qualcomm
/
MobileNet-v3-Small

Image Classification
PyTorch
TF Lite
ONNX
backbone
real_time
android
Model card Files Community
qaihm-bot commited on
Commit
905439f
·
verified ·
1 Parent(s): aa44518

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +28 -27
README.md CHANGED
@@ -37,38 +37,38 @@ More details on model performance across various devices, can be found
37
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
  | MobileNet-v3-Small | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.815 ms | 0 - 44 MB | FP16 | NPU | [MobileNet-v3-Small.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.tflite) |
40
- | MobileNet-v3-Small | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 0.873 ms | 0 - 33 MB | FP16 | NPU | [MobileNet-v3-Small.so](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.so) |
41
- | MobileNet-v3-Small | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 0.822 ms | 0 - 25 MB | FP16 | NPU | [MobileNet-v3-Small.onnx](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.onnx) |
42
- | MobileNet-v3-Small | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.544 ms | 0 - 20 MB | FP16 | NPU | [MobileNet-v3-Small.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.tflite) |
43
- | MobileNet-v3-Small | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.575 ms | 0 - 25 MB | FP16 | NPU | [MobileNet-v3-Small.so](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.so) |
44
- | MobileNet-v3-Small | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.587 ms | 1 - 33 MB | FP16 | NPU | [MobileNet-v3-Small.onnx](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.onnx) |
45
- | MobileNet-v3-Small | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.549 ms | 0 - 19 MB | FP16 | NPU | [MobileNet-v3-Small.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.tflite) |
46
- | MobileNet-v3-Small | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.48 ms | 0 - 16 MB | FP16 | NPU | Use Export Script |
47
- | MobileNet-v3-Small | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.498 ms | 0 - 20 MB | FP16 | NPU | [MobileNet-v3-Small.onnx](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.onnx) |
48
- | MobileNet-v3-Small | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.815 ms | 0 - 34 MB | FP16 | NPU | [MobileNet-v3-Small.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.tflite) |
49
- | MobileNet-v3-Small | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.841 ms | 1 - 4 MB | FP16 | NPU | Use Export Script |
50
- | MobileNet-v3-Small | SA7255P ADP | SA7255P | TFLITE | 7.735 ms | 0 - 13 MB | FP16 | NPU | [MobileNet-v3-Small.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.tflite) |
51
- | MobileNet-v3-Small | SA7255P ADP | SA7255P | QNN | 7.678 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
52
- | MobileNet-v3-Small | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.816 ms | 0 - 34 MB | FP16 | NPU | [MobileNet-v3-Small.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.tflite) |
53
- | MobileNet-v3-Small | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.843 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
54
- | MobileNet-v3-Small | SA8295P ADP | SA8295P | TFLITE | 1.547 ms | 0 - 18 MB | FP16 | NPU | [MobileNet-v3-Small.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.tflite) |
55
- | MobileNet-v3-Small | SA8295P ADP | SA8295P | QNN | 2.113 ms | 0 - 15 MB | FP16 | NPU | Use Export Script |
56
- | MobileNet-v3-Small | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.818 ms | 0 - 33 MB | FP16 | NPU | [MobileNet-v3-Small.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.tflite) |
57
- | MobileNet-v3-Small | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.84 ms | 1 - 4 MB | FP16 | NPU | Use Export Script |
58
- | MobileNet-v3-Small | SA8775P ADP | SA8775P | TFLITE | 1.373 ms | 0 - 12 MB | FP16 | NPU | [MobileNet-v3-Small.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.tflite) |
59
- | MobileNet-v3-Small | SA8775P ADP | SA8775P | QNN | 1.549 ms | 1 - 11 MB | FP16 | NPU | Use Export Script |
60
- | MobileNet-v3-Small | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 1.096 ms | 0 - 19 MB | FP16 | NPU | [MobileNet-v3-Small.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.tflite) |
61
- | MobileNet-v3-Small | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 1.145 ms | 1 - 20 MB | FP16 | NPU | Use Export Script |
62
- | MobileNet-v3-Small | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 0.967 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
63
- | MobileNet-v3-Small | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.867 ms | 8 - 8 MB | FP16 | NPU | [MobileNet-v3-Small.onnx](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.onnx) |
64
 
65
 
66
 
67
 
68
  ## Installation
69
 
70
- This model can be installed as a Python package via pip.
71
 
 
72
  ```bash
73
  pip install qai-hub-models
74
  ```
@@ -152,7 +152,7 @@ from qai_hub_models.models.mobilenet_v3_small import Model
152
  torch_model = Model.from_pretrained()
153
 
154
  # Device
155
- device = hub.Device("Samsung Galaxy S23")
156
 
157
  # Trace model
158
  input_shape = torch_model.get_input_spec()
@@ -244,7 +244,8 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
244
 
245
 
246
  ## License
247
- * The license for the original implementation of MobileNet-v3-Small can be found [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
 
 
37
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
  | MobileNet-v3-Small | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.815 ms | 0 - 44 MB | FP16 | NPU | [MobileNet-v3-Small.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.tflite) |
40
+ | MobileNet-v3-Small | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 0.856 ms | 0 - 33 MB | FP16 | NPU | [MobileNet-v3-Small.so](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.so) |
41
+ | MobileNet-v3-Small | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 0.817 ms | 0 - 32 MB | FP16 | NPU | [MobileNet-v3-Small.onnx](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.onnx) |
42
+ | MobileNet-v3-Small | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.538 ms | 0 - 21 MB | FP16 | NPU | [MobileNet-v3-Small.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.tflite) |
43
+ | MobileNet-v3-Small | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.573 ms | 0 - 22 MB | FP16 | NPU | [MobileNet-v3-Small.so](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.so) |
44
+ | MobileNet-v3-Small | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.543 ms | 0 - 27 MB | FP16 | NPU | [MobileNet-v3-Small.onnx](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.onnx) |
45
+ | MobileNet-v3-Small | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.553 ms | 0 - 19 MB | FP16 | NPU | [MobileNet-v3-Small.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.tflite) |
46
+ | MobileNet-v3-Small | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.586 ms | 1 - 19 MB | FP16 | NPU | Use Export Script |
47
+ | MobileNet-v3-Small | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.49 ms | 1 - 20 MB | FP16 | NPU | [MobileNet-v3-Small.onnx](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.onnx) |
48
+ | MobileNet-v3-Small | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.815 ms | 0 - 43 MB | FP16 | NPU | [MobileNet-v3-Small.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.tflite) |
49
+ | MobileNet-v3-Small | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.852 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
50
+ | MobileNet-v3-Small | SA7255P ADP | SA7255P | TFLITE | 7.671 ms | 0 - 12 MB | FP16 | NPU | [MobileNet-v3-Small.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.tflite) |
51
+ | MobileNet-v3-Small | SA7255P ADP | SA7255P | QNN | 7.553 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
52
+ | MobileNet-v3-Small | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.813 ms | 0 - 44 MB | FP16 | NPU | [MobileNet-v3-Small.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.tflite) |
53
+ | MobileNet-v3-Small | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.841 ms | 1 - 4 MB | FP16 | NPU | Use Export Script |
54
+ | MobileNet-v3-Small | SA8295P ADP | SA8295P | TFLITE | 1.564 ms | 0 - 18 MB | FP16 | NPU | [MobileNet-v3-Small.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.tflite) |
55
+ | MobileNet-v3-Small | SA8295P ADP | SA8295P | QNN | 1.763 ms | 0 - 14 MB | FP16 | NPU | Use Export Script |
56
+ | MobileNet-v3-Small | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.814 ms | 0 - 4 MB | FP16 | NPU | [MobileNet-v3-Small.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.tflite) |
57
+ | MobileNet-v3-Small | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.84 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
58
+ | MobileNet-v3-Small | SA8775P ADP | SA8775P | TFLITE | 1.368 ms | 0 - 13 MB | FP16 | NPU | [MobileNet-v3-Small.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.tflite) |
59
+ | MobileNet-v3-Small | SA8775P ADP | SA8775P | QNN | 1.524 ms | 1 - 11 MB | FP16 | NPU | Use Export Script |
60
+ | MobileNet-v3-Small | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 1.102 ms | 0 - 21 MB | FP16 | NPU | [MobileNet-v3-Small.tflite](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.tflite) |
61
+ | MobileNet-v3-Small | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 1.159 ms | 0 - 18 MB | FP16 | NPU | Use Export Script |
62
+ | MobileNet-v3-Small | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 0.959 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
63
+ | MobileNet-v3-Small | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.863 ms | 7 - 7 MB | FP16 | NPU | [MobileNet-v3-Small.onnx](https://huggingface.co/qualcomm/MobileNet-v3-Small/blob/main/MobileNet-v3-Small.onnx) |
64
 
65
 
66
 
67
 
68
  ## Installation
69
 
 
70
 
71
+ Install the package via pip:
72
  ```bash
73
  pip install qai-hub-models
74
  ```
 
152
  torch_model = Model.from_pretrained()
153
 
154
  # Device
155
+ device = hub.Device("Samsung Galaxy S24")
156
 
157
  # Trace model
158
  input_shape = torch_model.get_input_spec()
 
244
 
245
 
246
  ## License
247
+ * The license for the original implementation of MobileNet-v3-Small can be found
248
+ [here](https://github.com/pytorch/vision/blob/main/LICENSE).
249
  * 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)
250
 
251