Hugging Face's logo

qualcomm
/
ResNet101Quantized

Image Classification
PyTorch
TF Lite
ONNX
backbone
quantized
android
Model card Files Community
qaihm-bot commited on
Commit
0414527
·
verified ·
1 Parent(s): ab1d049

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +30 -29
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
- | ResNet101Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 1.17 ms | 0 - 56 MB | INT8 | NPU | [ResNet101Quantized.tflite](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.tflite) |
40
- | ResNet101Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 1.384 ms | 0 - 56 MB | INT8 | NPU | [ResNet101Quantized.so](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.so) |
41
- | ResNet101Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 2.149 ms | 0 - 82 MB | INT8 | NPU | [ResNet101Quantized.onnx](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.onnx) |
42
- | ResNet101Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.878 ms | 0 - 39 MB | INT8 | NPU | [ResNet101Quantized.tflite](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.tflite) |
43
- | ResNet101Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 1.075 ms | 0 - 27 MB | INT8 | NPU | [ResNet101Quantized.so](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.so) |
44
- | ResNet101Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 1.555 ms | 0 - 59 MB | INT8 | NPU | [ResNet101Quantized.onnx](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.onnx) |
45
- | ResNet101Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.83 ms | 0 - 25 MB | INT8 | NPU | [ResNet101Quantized.tflite](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.tflite) |
46
- | ResNet101Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.968 ms | 0 - 27 MB | INT8 | NPU | Use Export Script |
47
- | ResNet101Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 1.56 ms | 0 - 44 MB | INT8 | NPU | [ResNet101Quantized.onnx](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.onnx) |
48
- | ResNet101Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 4.595 ms | 0 - 31 MB | INT8 | NPU | [ResNet101Quantized.tflite](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.tflite) |
49
- | ResNet101Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 6.395 ms | 0 - 12 MB | INT8 | NPU | Use Export Script |
50
- | ResNet101Quantized | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 17.631 ms | 0 - 2 MB | INT8 | NPU | [ResNet101Quantized.tflite](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.tflite) |
51
- | ResNet101Quantized | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 1.165 ms | 0 - 46 MB | INT8 | NPU | [ResNet101Quantized.tflite](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.tflite) |
52
  | ResNet101Quantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 1.325 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
53
- | ResNet101Quantized | SA7255P ADP | SA7255P | TFLITE | 16.0 ms | 0 - 22 MB | INT8 | NPU | [ResNet101Quantized.tflite](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.tflite) |
54
- | ResNet101Quantized | SA7255P ADP | SA7255P | QNN | 16.92 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
55
- | ResNet101Quantized | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 1.165 ms | 0 - 56 MB | INT8 | NPU | [ResNet101Quantized.tflite](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.tflite) |
56
- | ResNet101Quantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 1.328 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
57
- | ResNet101Quantized | SA8295P ADP | SA8295P | TFLITE | 1.765 ms | 0 - 30 MB | INT8 | NPU | [ResNet101Quantized.tflite](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.tflite) |
58
- | ResNet101Quantized | SA8295P ADP | SA8295P | QNN | 2.23 ms | 0 - 14 MB | INT8 | NPU | Use Export Script |
59
- | ResNet101Quantized | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 1.167 ms | 0 - 26 MB | INT8 | NPU | [ResNet101Quantized.tflite](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.tflite) |
60
- | ResNet101Quantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 1.33 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
61
  | ResNet101Quantized | SA8775P ADP | SA8775P | TFLITE | 1.452 ms | 0 - 22 MB | INT8 | NPU | [ResNet101Quantized.tflite](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.tflite) |
62
- | ResNet101Quantized | SA8775P ADP | SA8775P | QNN | 1.812 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
63
- | ResNet101Quantized | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 1.406 ms | 0 - 44 MB | INT8 | NPU | [ResNet101Quantized.tflite](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.tflite) |
64
- | ResNet101Quantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 1.615 ms | 0 - 32 MB | INT8 | NPU | Use Export Script |
65
- | ResNet101Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 1.323 ms | 0 - 0 MB | INT8 | NPU | Use Export Script |
66
- | ResNet101Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 6.088 ms | 48 - 48 MB | INT8 | NPU | [ResNet101Quantized.onnx](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.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
  ```
@@ -155,7 +155,7 @@ from qai_hub_models.models.resnet101_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 ResNet101Quantized 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
+ | ResNet101Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 1.167 ms | 0 - 56 MB | INT8 | NPU | [ResNet101Quantized.tflite](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.tflite) |
40
+ | ResNet101Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 1.389 ms | 0 - 56 MB | INT8 | NPU | [ResNet101Quantized.so](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.so) |
41
+ | ResNet101Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 2.115 ms | 0 - 84 MB | INT8 | NPU | [ResNet101Quantized.onnx](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.onnx) |
42
+ | ResNet101Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.875 ms | 0 - 45 MB | INT8 | NPU | [ResNet101Quantized.tflite](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.tflite) |
43
+ | ResNet101Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 1.061 ms | 0 - 28 MB | INT8 | NPU | [ResNet101Quantized.so](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.so) |
44
+ | ResNet101Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 1.656 ms | 0 - 61 MB | INT8 | NPU | [ResNet101Quantized.onnx](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.onnx) |
45
+ | ResNet101Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.819 ms | 0 - 33 MB | INT8 | NPU | [ResNet101Quantized.tflite](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.tflite) |
46
+ | ResNet101Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.887 ms | 0 - 34 MB | INT8 | NPU | Use Export Script |
47
+ | ResNet101Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 1.558 ms | 0 - 46 MB | INT8 | NPU | [ResNet101Quantized.onnx](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.onnx) |
48
+ | ResNet101Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 4.489 ms | 0 - 30 MB | INT8 | NPU | [ResNet101Quantized.tflite](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.tflite) |
49
+ | ResNet101Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 6.394 ms | 0 - 11 MB | INT8 | NPU | Use Export Script |
50
+ | ResNet101Quantized | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 17.737 ms | 0 - 12 MB | INT8 | NPU | [ResNet101Quantized.tflite](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.tflite) |
51
+ | ResNet101Quantized | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 1.153 ms | 0 - 46 MB | INT8 | NPU | [ResNet101Quantized.tflite](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.tflite) |
52
  | ResNet101Quantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 1.325 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
53
+ | ResNet101Quantized | SA7255P ADP | SA7255P | TFLITE | 15.874 ms | 0 - 22 MB | INT8 | NPU | [ResNet101Quantized.tflite](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.tflite) |
54
+ | ResNet101Quantized | SA7255P ADP | SA7255P | QNN | 16.678 ms | 0 - 9 MB | INT8 | NPU | Use Export Script |
55
+ | ResNet101Quantized | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 1.172 ms | 0 - 46 MB | INT8 | NPU | [ResNet101Quantized.tflite](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.tflite) |
56
+ | ResNet101Quantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 1.327 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
57
+ | ResNet101Quantized | SA8295P ADP | SA8295P | TFLITE | 1.768 ms | 0 - 29 MB | INT8 | NPU | [ResNet101Quantized.tflite](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.tflite) |
58
+ | ResNet101Quantized | SA8295P ADP | SA8295P | QNN | 2.63 ms | 0 - 14 MB | INT8 | NPU | Use Export Script |
59
+ | ResNet101Quantized | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 1.167 ms | 0 - 56 MB | INT8 | NPU | [ResNet101Quantized.tflite](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.tflite) |
60
+ | ResNet101Quantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 1.328 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
61
  | ResNet101Quantized | SA8775P ADP | SA8775P | TFLITE | 1.452 ms | 0 - 22 MB | INT8 | NPU | [ResNet101Quantized.tflite](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.tflite) |
62
+ | ResNet101Quantized | SA8775P ADP | SA8775P | QNN | 1.83 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
63
+ | ResNet101Quantized | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 1.361 ms | 0 - 41 MB | INT8 | NPU | [ResNet101Quantized.tflite](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.tflite) |
64
+ | ResNet101Quantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 1.603 ms | 0 - 30 MB | INT8 | NPU | Use Export Script |
65
+ | ResNet101Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 1.359 ms | 0 - 0 MB | INT8 | NPU | Use Export Script |
66
+ | ResNet101Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2.173 ms | 48 - 48 MB | INT8 | NPU | [ResNet101Quantized.onnx](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.onnx) |
67
 
68
 
69
 
70
 
71
  ## Installation
72
 
 
73
 
74
+ Install the package via pip:
75
  ```bash
76
  pip install qai-hub-models
77
  ```
 
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 ResNet101Quantized 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