Hugging Face's logo

qualcomm
/
GoogLeNet

Image Classification
PyTorch
LiteRT
android
Model card Files Community
qaihm-bot commited on
Commit
40f7460
·
verified ·
1 Parent(s): 2c4b83e

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +27 -26
README.md CHANGED
@@ -35,38 +35,38 @@ More details on model performance across various devices, can be found
35
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
36
  |---|---|---|---|---|---|---|---|---|
37
  | GoogLeNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 1.016 ms | 0 - 54 MB | FP16 | NPU | [GoogLeNet.tflite](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.tflite) |
38
- | GoogLeNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 1.08 ms | 0 - 24 MB | FP16 | NPU | [GoogLeNet.so](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.so) |
39
- | GoogLeNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 1.153 ms | 0 - 47 MB | FP16 | NPU | [GoogLeNet.onnx](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.onnx) |
40
- | GoogLeNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.644 ms | 0 - 20 MB | FP16 | NPU | [GoogLeNet.tflite](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.tflite) |
41
- | GoogLeNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.687 ms | 0 - 21 MB | FP16 | NPU | [GoogLeNet.so](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.so) |
42
- | GoogLeNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.769 ms | 0 - 31 MB | FP16 | NPU | [GoogLeNet.onnx](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.onnx) |
43
- | GoogLeNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.676 ms | 0 - 18 MB | FP16 | NPU | [GoogLeNet.tflite](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.tflite) |
44
- | GoogLeNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.752 ms | 0 - 17 MB | FP16 | NPU | Use Export Script |
45
- | GoogLeNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.854 ms | 0 - 17 MB | FP16 | NPU | [GoogLeNet.onnx](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.onnx) |
46
- | GoogLeNet | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 1.017 ms | 0 - 54 MB | FP16 | NPU | [GoogLeNet.tflite](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.tflite) |
47
  | GoogLeNet | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.902 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
48
- | GoogLeNet | SA7255P ADP | SA7255P | TFLITE | 36.251 ms | 0 - 13 MB | FP16 | NPU | [GoogLeNet.tflite](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.tflite) |
49
- | GoogLeNet | SA7255P ADP | SA7255P | QNN | 36.393 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
50
- | GoogLeNet | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 1.013 ms | 0 - 55 MB | FP16 | NPU | [GoogLeNet.tflite](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.tflite) |
51
- | GoogLeNet | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.896 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
52
- | GoogLeNet | SA8295P ADP | SA8295P | TFLITE | 1.989 ms | 0 - 18 MB | FP16 | NPU | [GoogLeNet.tflite](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.tflite) |
53
- | GoogLeNet | SA8295P ADP | SA8295P | QNN | 2.16 ms | 1 - 15 MB | FP16 | NPU | Use Export Script |
54
- | GoogLeNet | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 1.024 ms | 0 - 44 MB | FP16 | NPU | [GoogLeNet.tflite](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.tflite) |
55
- | GoogLeNet | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.898 ms | 1 - 4 MB | FP16 | NPU | Use Export Script |
56
- | GoogLeNet | SA8775P ADP | SA8775P | TFLITE | 2.173 ms | 0 - 13 MB | FP16 | NPU | [GoogLeNet.tflite](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.tflite) |
57
- | GoogLeNet | SA8775P ADP | SA8775P | QNN | 2.144 ms | 1 - 11 MB | FP16 | NPU | Use Export Script |
58
- | GoogLeNet | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 1.489 ms | 0 - 24 MB | FP16 | NPU | [GoogLeNet.tflite](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.tflite) |
59
- | GoogLeNet | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 1.618 ms | 1 - 19 MB | FP16 | NPU | Use Export Script |
60
- | GoogLeNet | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 1.049 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
61
- | GoogLeNet | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 1.289 ms | 14 - 14 MB | FP16 | NPU | [GoogLeNet.onnx](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.onnx) |
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
  ```
@@ -150,7 +150,7 @@ from qai_hub_models.models.googlenet import Model
150
  torch_model = Model.from_pretrained()
151
 
152
  # Device
153
- device = hub.Device("Samsung Galaxy S23")
154
 
155
  # Trace model
156
  input_shape = torch_model.get_input_spec()
@@ -242,7 +242,8 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
242
 
243
 
244
  ## License
245
- * The license for the original implementation of GoogLeNet can be found [here](https://github.com/pytorch/vision/blob/main/LICENSE).
 
246
  * 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)
247
 
248
 
 
35
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
36
  |---|---|---|---|---|---|---|---|---|
37
  | GoogLeNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 1.016 ms | 0 - 54 MB | FP16 | NPU | [GoogLeNet.tflite](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.tflite) |
38
+ | GoogLeNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 1.086 ms | 0 - 35 MB | FP16 | NPU | [GoogLeNet.so](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.so) |
39
+ | GoogLeNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 1.142 ms | 0 - 45 MB | FP16 | NPU | [GoogLeNet.onnx](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.onnx) |
40
+ | GoogLeNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.64 ms | 0 - 20 MB | FP16 | NPU | [GoogLeNet.tflite](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.tflite) |
41
+ | GoogLeNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.688 ms | 1 - 19 MB | FP16 | NPU | [GoogLeNet.so](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.so) |
42
+ | GoogLeNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.822 ms | 1 - 28 MB | FP16 | NPU | [GoogLeNet.onnx](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.onnx) |
43
+ | GoogLeNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.679 ms | 0 - 22 MB | FP16 | NPU | [GoogLeNet.tflite](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.tflite) |
44
+ | GoogLeNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.599 ms | 1 - 19 MB | FP16 | NPU | Use Export Script |
45
+ | GoogLeNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.692 ms | 1 - 21 MB | FP16 | NPU | [GoogLeNet.onnx](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.onnx) |
46
+ | GoogLeNet | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 1.016 ms | 0 - 55 MB | FP16 | NPU | [GoogLeNet.tflite](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.tflite) |
47
  | GoogLeNet | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.902 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
48
+ | GoogLeNet | SA7255P ADP | SA7255P | TFLITE | 36.132 ms | 0 - 13 MB | FP16 | NPU | [GoogLeNet.tflite](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.tflite) |
49
+ | GoogLeNet | SA7255P ADP | SA7255P | QNN | 36.268 ms | 1 - 9 MB | FP16 | NPU | Use Export Script |
50
+ | GoogLeNet | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 1.014 ms | 0 - 44 MB | FP16 | NPU | [GoogLeNet.tflite](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.tflite) |
51
+ | GoogLeNet | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.895 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
52
+ | GoogLeNet | SA8295P ADP | SA8295P | TFLITE | 1.994 ms | 0 - 18 MB | FP16 | NPU | [GoogLeNet.tflite](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.tflite) |
53
+ | GoogLeNet | SA8295P ADP | SA8295P | QNN | 2.155 ms | 0 - 14 MB | FP16 | NPU | Use Export Script |
54
+ | GoogLeNet | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 1.015 ms | 0 - 54 MB | FP16 | NPU | [GoogLeNet.tflite](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.tflite) |
55
+ | GoogLeNet | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.902 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
56
+ | GoogLeNet | SA8775P ADP | SA8775P | TFLITE | 2.17 ms | 0 - 13 MB | FP16 | NPU | [GoogLeNet.tflite](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.tflite) |
57
+ | GoogLeNet | SA8775P ADP | SA8775P | QNN | 2.116 ms | 0 - 10 MB | FP16 | NPU | Use Export Script |
58
+ | GoogLeNet | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 1.497 ms | 0 - 26 MB | FP16 | NPU | [GoogLeNet.tflite](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.tflite) |
59
+ | GoogLeNet | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 1.566 ms | 1 - 25 MB | FP16 | NPU | Use Export Script |
60
+ | GoogLeNet | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 1.038 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
61
+ | GoogLeNet | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 1.32 ms | 15 - 15 MB | FP16 | NPU | [GoogLeNet.onnx](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.onnx) |
62
 
63
 
64
 
65
 
66
  ## Installation
67
 
 
68
 
69
+ Install the package via pip:
70
  ```bash
71
  pip install qai-hub-models
72
  ```
 
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 GoogLeNet can be found
246
+ [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