Hugging Face's logo

qualcomm
/
GoogLeNetQuantized

Image Classification
PyTorch
TF Lite
ONNX
quantized
android
Model card Files Community
qaihm-bot commited on
Commit
2fed0eb
·
verified ·
1 Parent(s): 32b0f56

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +31 -30
README.md CHANGED
@@ -35,42 +35,42 @@ 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
- | GoogLeNetQuantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.284 ms | 0 - 11 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
39
- | GoogLeNetQuantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 0.343 ms | 0 - 14 MB | INT8 | NPU | [GoogLeNetQuantized.so](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.so) |
40
- | GoogLeNetQuantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 0.526 ms | 0 - 31 MB | INT8 | NPU | [GoogLeNetQuantized.onnx](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.onnx) |
41
- | GoogLeNetQuantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.213 ms | 0 - 22 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
42
- | GoogLeNetQuantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.25 ms | 0 - 28 MB | INT8 | NPU | [GoogLeNetQuantized.so](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.so) |
43
- | GoogLeNetQuantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.37 ms | 0 - 28 MB | INT8 | NPU | [GoogLeNetQuantized.onnx](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.onnx) |
44
- | GoogLeNetQuantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.22 ms | 0 - 18 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
45
- | GoogLeNetQuantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.27 ms | 0 - 18 MB | INT8 | NPU | Use Export Script |
46
- | GoogLeNetQuantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.42 ms | 0 - 23 MB | INT8 | NPU | [GoogLeNetQuantized.onnx](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.onnx) |
47
- | GoogLeNetQuantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 0.896 ms | 0 - 16 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
48
- | GoogLeNetQuantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 1.155 ms | 0 - 12 MB | INT8 | NPU | Use Export Script |
49
- | GoogLeNetQuantized | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 6.302 ms | 0 - 2 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
50
- | GoogLeNetQuantized | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.287 ms | 0 - 13 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
51
- | GoogLeNetQuantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.308 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
52
- | GoogLeNetQuantized | SA7255P ADP | SA7255P | TFLITE | 3.767 ms | 0 - 13 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
53
- | GoogLeNetQuantized | SA7255P ADP | SA7255P | QNN | 4.004 ms | 0 - 9 MB | INT8 | NPU | Use Export Script |
54
- | GoogLeNetQuantized | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.28 ms | 0 - 15 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
55
  | GoogLeNetQuantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.302 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
56
- | GoogLeNetQuantized | SA8295P ADP | SA8295P | TFLITE | 0.646 ms | 0 - 18 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
57
- | GoogLeNetQuantized | SA8295P ADP | SA8295P | QNN | 1.276 ms | 0 - 14 MB | INT8 | NPU | Use Export Script |
58
- | GoogLeNetQuantized | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.285 ms | 0 - 14 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
59
  | GoogLeNetQuantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.304 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
60
- | GoogLeNetQuantized | SA8775P ADP | SA8775P | TFLITE | 0.582 ms | 0 - 12 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
61
- | GoogLeNetQuantized | SA8775P ADP | SA8775P | QNN | 0.76 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
62
- | GoogLeNetQuantized | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 0.356 ms | 0 - 20 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
63
- | GoogLeNetQuantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 0.406 ms | 0 - 25 MB | INT8 | NPU | Use Export Script |
64
- | GoogLeNetQuantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 0.414 ms | 0 - 0 MB | INT8 | NPU | Use Export Script |
65
- | GoogLeNetQuantized | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.551 ms | 9 - 9 MB | INT8 | NPU | [GoogLeNetQuantized.onnx](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.onnx) |
66
 
67
 
68
 
69
 
70
  ## Installation
71
 
72
- This model can be installed as a Python package via pip.
73
 
 
74
  ```bash
75
  pip install qai-hub-models
76
  ```
@@ -127,7 +127,7 @@ GoogLeNetQuantized
127
  Device : Samsung Galaxy S23 (13)
128
  Runtime : TFLITE
129
  Estimated inference time (ms) : 0.3
130
- Estimated peak memory usage (MB): [0, 11]
131
  Total # Ops : 86
132
  Compute Unit(s) : NPU (86 ops)
133
  ```
@@ -154,7 +154,7 @@ from qai_hub_models.models.googlenet_quantized import Model
154
  torch_model = Model.from_pretrained()
155
 
156
  # Device
157
- device = hub.Device("Samsung Galaxy S23")
158
 
159
  # Trace model
160
  input_shape = torch_model.get_input_spec()
@@ -246,7 +246,8 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
246
 
247
 
248
  ## License
249
- * The license for the original implementation of GoogLeNetQuantized can be found [here](https://github.com/pytorch/vision/blob/main/LICENSE).
 
250
  * 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)
251
 
252
 
 
35
 
36
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | GoogLeNetQuantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.284 ms | 0 - 14 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
39
+ | GoogLeNetQuantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 0.343 ms | 0 - 13 MB | INT8 | NPU | [GoogLeNetQuantized.so](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.so) |
40
+ | GoogLeNetQuantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 0.533 ms | 0 - 29 MB | INT8 | NPU | [GoogLeNetQuantized.onnx](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.onnx) |
41
+ | GoogLeNetQuantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.197 ms | 0 - 18 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
42
+ | GoogLeNetQuantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.25 ms | 0 - 26 MB | INT8 | NPU | [GoogLeNetQuantized.so](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.so) |
43
+ | GoogLeNetQuantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.371 ms | 0 - 27 MB | INT8 | NPU | [GoogLeNetQuantized.onnx](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.onnx) |
44
+ | GoogLeNetQuantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.218 ms | 0 - 19 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
45
+ | GoogLeNetQuantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.255 ms | 0 - 18 MB | INT8 | NPU | Use Export Script |
46
+ | GoogLeNetQuantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.403 ms | 0 - 22 MB | INT8 | NPU | [GoogLeNetQuantized.onnx](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.onnx) |
47
+ | GoogLeNetQuantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 0.902 ms | 0 - 16 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
48
+ | GoogLeNetQuantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 1.172 ms | 0 - 11 MB | INT8 | NPU | Use Export Script |
49
+ | GoogLeNetQuantized | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 6.023 ms | 0 - 3 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
50
+ | GoogLeNetQuantized | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.288 ms | 0 - 14 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
51
+ | GoogLeNetQuantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.307 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
52
+ | GoogLeNetQuantized | SA7255P ADP | SA7255P | TFLITE | 3.613 ms | 0 - 12 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
53
+ | GoogLeNetQuantized | SA7255P ADP | SA7255P | QNN | 3.901 ms | 0 - 9 MB | INT8 | NPU | Use Export Script |
54
+ | GoogLeNetQuantized | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.282 ms | 0 - 13 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
55
  | GoogLeNetQuantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.302 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
56
+ | GoogLeNetQuantized | SA8295P ADP | SA8295P | TFLITE | 0.648 ms | 0 - 18 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
57
+ | GoogLeNetQuantized | SA8295P ADP | SA8295P | QNN | 1.027 ms | 0 - 14 MB | INT8 | NPU | Use Export Script |
58
+ | GoogLeNetQuantized | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.283 ms | 0 - 14 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
59
  | GoogLeNetQuantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.304 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
60
+ | GoogLeNetQuantized | SA8775P ADP | SA8775P | TFLITE | 0.578 ms | 0 - 12 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
61
+ | GoogLeNetQuantized | SA8775P ADP | SA8775P | QNN | 0.771 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
62
+ | GoogLeNetQuantized | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 0.343 ms | 0 - 15 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite) |
63
+ | GoogLeNetQuantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 0.417 ms | 0 - 24 MB | INT8 | NPU | Use Export Script |
64
+ | GoogLeNetQuantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 0.406 ms | 0 - 0 MB | INT8 | NPU | Use Export Script |
65
+ | GoogLeNetQuantized | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.578 ms | 9 - 9 MB | INT8 | NPU | [GoogLeNetQuantized.onnx](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.onnx) |
66
 
67
 
68
 
69
 
70
  ## Installation
71
 
 
72
 
73
+ Install the package via pip:
74
  ```bash
75
  pip install qai-hub-models
76
  ```
 
127
  Device : Samsung Galaxy S23 (13)
128
  Runtime : TFLITE
129
  Estimated inference time (ms) : 0.3
130
+ Estimated peak memory usage (MB): [0, 14]
131
  Total # Ops : 86
132
  Compute Unit(s) : NPU (86 ops)
133
  ```
 
154
  torch_model = Model.from_pretrained()
155
 
156
  # Device
157
+ device = hub.Device("Samsung Galaxy S24")
158
 
159
  # Trace model
160
  input_shape = torch_model.get_input_spec()
 
246
 
247
 
248
  ## License
249
+ * The license for the original implementation of GoogLeNetQuantized can be found
250
+ [here](https://github.com/pytorch/vision/blob/main/LICENSE).
251
  * 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)
252
 
253