Hugging Face's logo

qualcomm
/
MNASNet05

Image Classification
PyTorch
LiteRT
ONNX
backbone
android
Model card Files Community
qaihm-bot commited on
Commit
72ce28e
·
verified ·
1 Parent(s): 1f62517

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +26 -25
README.md CHANGED
@@ -35,30 +35,30 @@ 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
- | MNASNet05 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.755 ms | 0 - 32 MB | FP16 | NPU | [MNASNet05.tflite](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.tflite) |
39
- | MNASNet05 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 0.825 ms | 0 - 32 MB | FP16 | NPU | [MNASNet05.so](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.so) |
40
- | MNASNet05 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 0.752 ms | 0 - 24 MB | FP16 | NPU | [MNASNet05.onnx](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.onnx) |
41
- | MNASNet05 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.513 ms | 0 - 19 MB | FP16 | NPU | [MNASNet05.tflite](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.tflite) |
42
- | MNASNet05 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.562 ms | 1 - 23 MB | FP16 | NPU | [MNASNet05.so](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.so) |
43
- | MNASNet05 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.52 ms | 0 - 29 MB | FP16 | NPU | [MNASNet05.onnx](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.onnx) |
44
  | MNASNet05 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.42 ms | 0 - 19 MB | FP16 | NPU | [MNASNet05.tflite](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.tflite) |
45
- | MNASNet05 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.58 ms | 0 - 19 MB | FP16 | NPU | Use Export Script |
46
- | MNASNet05 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.603 ms | 0 - 23 MB | FP16 | NPU | [MNASNet05.onnx](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.onnx) |
47
- | MNASNet05 | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.758 ms | 0 - 43 MB | FP16 | NPU | [MNASNet05.tflite](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.tflite) |
48
- | MNASNet05 | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.769 ms | 1 - 4 MB | FP16 | NPU | Use Export Script |
49
- | MNASNet05 | SA7255P ADP | SA7255P | TFLITE | 10.825 ms | 0 - 13 MB | FP16 | NPU | [MNASNet05.tflite](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.tflite) |
50
- | MNASNet05 | SA7255P ADP | SA7255P | QNN | 11.051 ms | 1 - 11 MB | FP16 | NPU | Use Export Script |
51
- | MNASNet05 | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.76 ms | 0 - 32 MB | FP16 | NPU | [MNASNet05.tflite](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.tflite) |
52
- | MNASNet05 | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.766 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
53
- | MNASNet05 | SA8295P ADP | SA8295P | TFLITE | 1.451 ms | 0 - 18 MB | FP16 | NPU | [MNASNet05.tflite](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.tflite) |
54
- | MNASNet05 | SA8295P ADP | SA8295P | QNN | 1.672 ms | 0 - 14 MB | FP16 | NPU | Use Export Script |
55
- | MNASNet05 | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.758 ms | 0 - 33 MB | FP16 | NPU | [MNASNet05.tflite](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.tflite) |
56
  | MNASNet05 | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.764 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
57
- | MNASNet05 | SA8775P ADP | SA8775P | TFLITE | 1.337 ms | 0 - 13 MB | FP16 | NPU | [MNASNet05.tflite](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.tflite) |
58
- | MNASNet05 | SA8775P ADP | SA8775P | QNN | 1.508 ms | 1 - 11 MB | FP16 | NPU | Use Export Script |
59
- | MNASNet05 | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 1.027 ms | 0 - 16 MB | FP16 | NPU | [MNASNet05.tflite](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.tflite) |
60
- | MNASNet05 | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 1.139 ms | 1 - 19 MB | FP16 | NPU | Use Export Script |
61
- | MNASNet05 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 0.899 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
62
  | MNASNet05 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.816 ms | 7 - 7 MB | FP16 | NPU | [MNASNet05.onnx](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.onnx) |
63
 
64
 
@@ -66,8 +66,8 @@ More details on model performance across various devices, can be found
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
  ```
@@ -151,7 +151,7 @@ from qai_hub_models.models.mnasnet05 import Model
151
  torch_model = Model.from_pretrained()
152
 
153
  # Device
154
- device = hub.Device("Samsung Galaxy S23")
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 MNASNet05 can be found [here](https://github.com/pytorch/vision/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
 
 
35
 
36
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | MNASNet05 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.76 ms | 0 - 32 MB | FP16 | NPU | [MNASNet05.tflite](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.tflite) |
39
+ | MNASNet05 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 0.828 ms | 0 - 33 MB | FP16 | NPU | [MNASNet05.so](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.so) |
40
+ | MNASNet05 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 0.74 ms | 0 - 23 MB | FP16 | NPU | [MNASNet05.onnx](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.onnx) |
41
+ | MNASNet05 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.511 ms | 0 - 28 MB | FP16 | NPU | [MNASNet05.tflite](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.tflite) |
42
+ | MNASNet05 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.558 ms | 1 - 26 MB | FP16 | NPU | [MNASNet05.so](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.so) |
43
+ | MNASNet05 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.516 ms | 0 - 32 MB | FP16 | NPU | [MNASNet05.onnx](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.onnx) |
44
  | MNASNet05 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.42 ms | 0 - 19 MB | FP16 | NPU | [MNASNet05.tflite](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.tflite) |
45
+ | MNASNet05 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.559 ms | 1 - 19 MB | FP16 | NPU | Use Export Script |
46
+ | MNASNet05 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.574 ms | 1 - 20 MB | FP16 | NPU | [MNASNet05.onnx](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.onnx) |
47
+ | MNASNet05 | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.756 ms | 0 - 42 MB | FP16 | NPU | [MNASNet05.tflite](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.tflite) |
48
+ | MNASNet05 | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.761 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
49
+ | MNASNet05 | SA7255P ADP | SA7255P | TFLITE | 10.728 ms | 0 - 12 MB | FP16 | NPU | [MNASNet05.tflite](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.tflite) |
50
+ | MNASNet05 | SA7255P ADP | SA7255P | QNN | 10.96 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
51
+ | MNASNet05 | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.759 ms | 0 - 32 MB | FP16 | NPU | [MNASNet05.tflite](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.tflite) |
52
+ | MNASNet05 | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.759 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
53
+ | MNASNet05 | SA8295P ADP | SA8295P | TFLITE | 1.444 ms | 0 - 18 MB | FP16 | NPU | [MNASNet05.tflite](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.tflite) |
54
+ | MNASNet05 | SA8295P ADP | SA8295P | QNN | 1.724 ms | 0 - 14 MB | FP16 | NPU | Use Export Script |
55
+ | MNASNet05 | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.758 ms | 0 - 22 MB | FP16 | NPU | [MNASNet05.tflite](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.tflite) |
56
  | MNASNet05 | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.764 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
57
+ | MNASNet05 | SA8775P ADP | SA8775P | TFLITE | 1.333 ms | 0 - 14 MB | FP16 | NPU | [MNASNet05.tflite](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.tflite) |
58
+ | MNASNet05 | SA8775P ADP | SA8775P | QNN | 1.547 ms | 0 - 10 MB | FP16 | NPU | Use Export Script |
59
+ | MNASNet05 | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 1.047 ms | 0 - 18 MB | FP16 | NPU | [MNASNet05.tflite](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.tflite) |
60
+ | MNASNet05 | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 1.142 ms | 1 - 22 MB | FP16 | NPU | Use Export Script |
61
+ | MNASNet05 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 0.908 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
62
  | MNASNet05 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.816 ms | 7 - 7 MB | FP16 | NPU | [MNASNet05.onnx](https://huggingface.co/qualcomm/MNASNet05/blob/main/MNASNet05.onnx) |
63
 
64
 
 
66
 
67
  ## Installation
68
 
 
69
 
70
+ Install the package via pip:
71
  ```bash
72
  pip install qai-hub-models
73
  ```
 
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 MNASNet05 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