Hugging Face's logo

qualcomm
/
Inception-v3-Quantized

Image Classification
PyTorch
LiteRT
ONNX
backbone
quantized
android
Model card Files Community
qaihm-bot commited on
Commit
a9cd55b
·
verified ·
1 Parent(s): cadac2f

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +33 -32
README.md CHANGED
@@ -36,42 +36,42 @@ More details on model performance across various devices, can be found
36
 
37
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
- | Inception-v3-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.644 ms | 0 - 38 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
40
- | Inception-v3-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 0.647 ms | 0 - 38 MB | INT8 | NPU | [Inception-v3-Quantized.so](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.so) |
41
- | Inception-v3-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 0.896 ms | 0 - 68 MB | INT8 | NPU | [Inception-v3-Quantized.onnx](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.onnx) |
42
- | Inception-v3-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.472 ms | 0 - 29 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
43
- | Inception-v3-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.507 ms | 0 - 24 MB | INT8 | NPU | [Inception-v3-Quantized.so](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.so) |
44
- | Inception-v3-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.682 ms | 0 - 42 MB | INT8 | NPU | [Inception-v3-Quantized.onnx](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.onnx) |
45
- | Inception-v3-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.449 ms | 0 - 24 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
46
- | Inception-v3-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.491 ms | 0 - 22 MB | INT8 | NPU | Use Export Script |
47
- | Inception-v3-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.659 ms | 0 - 27 MB | INT8 | NPU | [Inception-v3-Quantized.onnx](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.onnx) |
48
- | Inception-v3-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 2.462 ms | 0 - 25 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
49
- | Inception-v3-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 2.873 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
50
- | Inception-v3-Quantized | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 7.982 ms | 0 - 12 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
51
- | Inception-v3-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.645 ms | 0 - 38 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
52
- | Inception-v3-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.654 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
53
- | Inception-v3-Quantized | SA7255P ADP | SA7255P | TFLITE | 8.458 ms | 0 - 18 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
54
- | Inception-v3-Quantized | SA7255P ADP | SA7255P | QNN | 8.745 ms | 0 - 9 MB | INT8 | NPU | Use Export Script |
55
- | Inception-v3-Quantized | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.645 ms | 0 - 38 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
56
- | Inception-v3-Quantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.661 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
57
- | Inception-v3-Quantized | SA8295P ADP | SA8295P | TFLITE | 1.147 ms | 0 - 23 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
58
- | Inception-v3-Quantized | SA8295P ADP | SA8295P | QNN | 1.473 ms | 0 - 15 MB | INT8 | NPU | Use Export Script |
59
- | Inception-v3-Quantized | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.644 ms | 0 - 39 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
60
- | Inception-v3-Quantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.654 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
61
- | Inception-v3-Quantized | SA8775P ADP | SA8775P | TFLITE | 0.96 ms | 0 - 18 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
62
- | Inception-v3-Quantized | SA8775P ADP | SA8775P | QNN | 1.107 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
63
- | Inception-v3-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 0.778 ms | 0 - 28 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
64
- | Inception-v3-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 0.778 ms | 0 - 30 MB | INT8 | NPU | Use Export Script |
65
- | Inception-v3-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 0.876 ms | 0 - 0 MB | INT8 | NPU | Use Export Script |
66
- | Inception-v3-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.816 ms | 26 - 26 MB | INT8 | NPU | [Inception-v3-Quantized.onnx](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.onnx) |
67
 
68
 
69
 
70
 
71
  ## Installation
72
 
73
- This model can be installed as a Python package via pip.
74
 
 
75
  ```bash
76
  pip install qai-hub-models
77
  ```
@@ -128,7 +128,7 @@ Inception-v3-Quantized
128
  Device : Samsung Galaxy S23 (13)
129
  Runtime : TFLITE
130
  Estimated inference time (ms) : 0.6
131
- Estimated peak memory usage (MB): [0, 38]
132
  Total # Ops : 142
133
  Compute Unit(s) : NPU (142 ops)
134
  ```
@@ -155,7 +155,7 @@ from qai_hub_models.models.inception_v3_quantized import Model
155
  torch_model = Model.from_pretrained()
156
 
157
  # Device
158
- device = hub.Device("Samsung Galaxy S23")
159
 
160
  # Trace model
161
  input_shape = torch_model.get_input_spec()
@@ -247,7 +247,8 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
247
 
248
 
249
  ## License
250
- * The license for the original implementation of Inception-v3-Quantized can be found [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
 
 
36
 
37
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
+ | Inception-v3-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.646 ms | 0 - 40 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
40
+ | Inception-v3-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 0.651 ms | 0 - 37 MB | INT8 | NPU | [Inception-v3-Quantized.so](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.so) |
41
+ | Inception-v3-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 0.897 ms | 0 - 70 MB | INT8 | NPU | [Inception-v3-Quantized.onnx](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.onnx) |
42
+ | Inception-v3-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.469 ms | 0 - 25 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
43
+ | Inception-v3-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.497 ms | 0 - 30 MB | INT8 | NPU | [Inception-v3-Quantized.so](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.so) |
44
+ | Inception-v3-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.66 ms | 0 - 41 MB | INT8 | NPU | [Inception-v3-Quantized.onnx](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.onnx) |
45
+ | Inception-v3-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.459 ms | 0 - 24 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
46
+ | Inception-v3-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.518 ms | 0 - 23 MB | INT8 | NPU | Use Export Script |
47
+ | Inception-v3-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.656 ms | 0 - 31 MB | INT8 | NPU | [Inception-v3-Quantized.onnx](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.onnx) |
48
+ | Inception-v3-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 2.442 ms | 0 - 24 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
49
+ | Inception-v3-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 2.942 ms | 0 - 12 MB | INT8 | NPU | Use Export Script |
50
+ | Inception-v3-Quantized | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 8.09 ms | 0 - 3 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
51
+ | Inception-v3-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.682 ms | 0 - 6 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
52
+ | Inception-v3-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.653 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
53
+ | Inception-v3-Quantized | SA7255P ADP | SA7255P | TFLITE | 8.403 ms | 0 - 17 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
54
+ | Inception-v3-Quantized | SA7255P ADP | SA7255P | QNN | 8.636 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
55
+ | Inception-v3-Quantized | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.647 ms | 0 - 39 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
56
+ | Inception-v3-Quantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.656 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
57
+ | Inception-v3-Quantized | SA8295P ADP | SA8295P | TFLITE | 1.138 ms | 0 - 23 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
58
+ | Inception-v3-Quantized | SA8295P ADP | SA8295P | QNN | 1.431 ms | 0 - 14 MB | INT8 | NPU | Use Export Script |
59
+ | Inception-v3-Quantized | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.638 ms | 0 - 39 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
60
+ | Inception-v3-Quantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.654 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
61
+ | Inception-v3-Quantized | SA8775P ADP | SA8775P | TFLITE | 0.951 ms | 0 - 18 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
62
+ | Inception-v3-Quantized | SA8775P ADP | SA8775P | QNN | 1.096 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
63
+ | Inception-v3-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 0.76 ms | 0 - 23 MB | INT8 | NPU | [Inception-v3-Quantized.tflite](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.tflite) |
64
+ | Inception-v3-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 0.808 ms | 0 - 31 MB | INT8 | NPU | Use Export Script |
65
+ | Inception-v3-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 0.708 ms | 0 - 0 MB | INT8 | NPU | Use Export Script |
66
+ | Inception-v3-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.786 ms | 27 - 27 MB | INT8 | NPU | [Inception-v3-Quantized.onnx](https://huggingface.co/qualcomm/Inception-v3-Quantized/blob/main/Inception-v3-Quantized.onnx) |
67
 
68
 
69
 
70
 
71
  ## Installation
72
 
 
73
 
74
+ Install the package via pip:
75
  ```bash
76
  pip install qai-hub-models
77
  ```
 
128
  Device : Samsung Galaxy S23 (13)
129
  Runtime : TFLITE
130
  Estimated inference time (ms) : 0.6
131
+ Estimated peak memory usage (MB): [0, 40]
132
  Total # Ops : 142
133
  Compute Unit(s) : NPU (142 ops)
134
  ```
 
155
  torch_model = Model.from_pretrained()
156
 
157
  # Device
158
+ device = hub.Device("Samsung Galaxy S24")
159
 
160
  # Trace model
161
  input_shape = torch_model.get_input_spec()
 
247
 
248
 
249
  ## License
250
+ * The license for the original implementation of Inception-v3-Quantized can be found
251
+ [here](https://github.com/pytorch/vision/blob/main/LICENSE).
252
  * 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)
253
 
254