Hugging Face's logo

qualcomm
/
Swin-Base

Image Classification
PyTorch
LiteRT
ONNX
backbone
android
Model card Files Community
qaihm-bot commited on
Commit
423e7f9
·
verified ·
1 Parent(s): 2eaa10b

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +30 -30
README.md CHANGED
@@ -35,39 +35,38 @@ 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
- | Swin-Base | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 26.047 ms | 0 - 44 MB | FP16 | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
39
- | Swin-Base | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 26.357 ms | 0 - 43 MB | FP16 | NPU | [Swin-Base.so](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.so) |
40
- | Swin-Base | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 43.123 ms | 0 - 351 MB | FP16 | NPU | [Swin-Base.onnx](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.onnx) |
41
- | Swin-Base | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 18.35 ms | 0 - 204 MB | FP16 | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
42
- | Swin-Base | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 18.041 ms | 0 - 200 MB | FP16 | NPU | [Swin-Base.so](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.so) |
43
- | Swin-Base | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 29.802 ms | 1 - 223 MB | FP16 | NPU | [Swin-Base.onnx](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.onnx) |
44
- | Swin-Base | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 14.205 ms | 0 - 204 MB | FP16 | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
45
- | Swin-Base | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 16.453 ms | 20 - 230 MB | FP16 | NPU | Use Export Script |
46
- | Swin-Base | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 27.226 ms | 0 - 236 MB | FP16 | NPU | [Swin-Base.onnx](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.onnx) |
47
- | Swin-Base | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 26.373 ms | 0 - 44 MB | FP16 | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
48
- | Swin-Base | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 23.86 ms | 1 - 4 MB | FP16 | NPU | Use Export Script |
49
- | Swin-Base | SA7255P ADP | SA7255P | TFLITE | 307.274 ms | 0 - 205 MB | FP16 | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
50
- | Swin-Base | SA7255P ADP | SA7255P | QNN | 303.152 ms | 1 - 9 MB | FP16 | NPU | Use Export Script |
51
- | Swin-Base | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 26.519 ms | 0 - 41 MB | FP16 | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
52
- | Swin-Base | SA8255 (Proxy) | SA8255P Proxy | QNN | 24.003 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
53
- | Swin-Base | SA8295P ADP | SA8295P | TFLITE | 36.816 ms | 0 - 192 MB | FP16 | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
54
- | Swin-Base | SA8295P ADP | SA8295P | QNN | 34.585 ms | 1 - 15 MB | FP16 | NPU | Use Export Script |
55
- | Swin-Base | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 26.213 ms | 0 - 42 MB | FP16 | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
56
- | Swin-Base | SA8650 (Proxy) | SA8650P Proxy | QNN | 23.825 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
57
- | Swin-Base | SA8775P ADP | SA8775P | TFLITE | 35.646 ms | 0 - 206 MB | FP16 | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
58
- | Swin-Base | SA8775P ADP | SA8775P | QNN | 33.072 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
59
- | Swin-Base | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 33.465 ms | 0 - 190 MB | FP16 | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
60
- | Swin-Base | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 34.001 ms | 1 - 194 MB | FP16 | NPU | Use Export Script |
61
- | Swin-Base | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 24.389 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
62
- | Swin-Base | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 50.174 ms | 176 - 176 MB | FP16 | NPU | [Swin-Base.onnx](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.onnx) |
63
 
64
 
65
 
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
  ```
@@ -123,8 +122,8 @@ Profiling Results
123
  Swin-Base
124
  Device : Samsung Galaxy S23 (13)
125
  Runtime : TFLITE
126
- Estimated inference time (ms) : 26.0
127
- Estimated peak memory usage (MB): [0, 44]
128
  Total # Ops : 1568
129
  Compute Unit(s) : NPU (1568 ops)
130
  ```
@@ -151,7 +150,7 @@ from qai_hub_models.models.swin_base 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 +242,8 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
243
 
244
 
245
  ## License
246
- * The license for the original implementation of Swin-Base 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
+ | Swin-Base | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 26.254 ms | 0 - 37 MB | FP16 | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
39
+ | Swin-Base | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 26.363 ms | 0 - 47 MB | FP16 | NPU | [Swin-Base.so](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.so) |
40
+ | Swin-Base | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 43.137 ms | 0 - 363 MB | FP16 | NPU | [Swin-Base.onnx](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.onnx) |
41
+ | Swin-Base | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 18.054 ms | 0 - 201 MB | FP16 | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
42
+ | Swin-Base | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 18.304 ms | 0 - 201 MB | FP16 | NPU | [Swin-Base.so](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.so) |
43
+ | Swin-Base | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 29.96 ms | 1 - 221 MB | FP16 | NPU | [Swin-Base.onnx](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.onnx) |
44
+ | Swin-Base | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 16.754 ms | 0 - 208 MB | FP16 | NPU | Use Export Script |
45
+ | Swin-Base | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 27.191 ms | 1 - 236 MB | FP16 | NPU | [Swin-Base.onnx](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.onnx) |
46
+ | Swin-Base | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 26.238 ms | 0 - 43 MB | FP16 | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
47
+ | Swin-Base | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 23.622 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
48
+ | Swin-Base | SA7255P ADP | SA7255P | TFLITE | 307.209 ms | 0 - 205 MB | FP16 | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
49
+ | Swin-Base | SA7255P ADP | SA7255P | QNN | 303.103 ms | 1 - 9 MB | FP16 | NPU | Use Export Script |
50
+ | Swin-Base | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 26.379 ms | 0 - 41 MB | FP16 | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
51
+ | Swin-Base | SA8255 (Proxy) | SA8255P Proxy | QNN | 23.855 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
52
+ | Swin-Base | SA8295P ADP | SA8295P | TFLITE | 36.841 ms | 0 - 193 MB | FP16 | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
53
+ | Swin-Base | SA8295P ADP | SA8295P | QNN | 34.628 ms | 1 - 15 MB | FP16 | NPU | Use Export Script |
54
+ | Swin-Base | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 26.333 ms | 0 - 41 MB | FP16 | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
55
+ | Swin-Base | SA8650 (Proxy) | SA8650P Proxy | QNN | 23.835 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
56
+ | Swin-Base | SA8775P ADP | SA8775P | TFLITE | 35.701 ms | 0 - 205 MB | FP16 | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
57
+ | Swin-Base | SA8775P ADP | SA8775P | QNN | 33.046 ms | 1 - 11 MB | FP16 | NPU | Use Export Script |
58
+ | Swin-Base | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 34.112 ms | 0 - 189 MB | FP16 | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) |
59
+ | Swin-Base | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 33.702 ms | 1 - 194 MB | FP16 | NPU | Use Export Script |
60
+ | Swin-Base | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 24.417 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
61
+ | Swin-Base | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 50.171 ms | 175 - 175 MB | FP16 | NPU | [Swin-Base.onnx](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.onnx) |
 
62
 
63
 
64
 
65
 
66
  ## Installation
67
 
 
68
 
69
+ Install the package via pip:
70
  ```bash
71
  pip install qai-hub-models
72
  ```
 
122
  Swin-Base
123
  Device : Samsung Galaxy S23 (13)
124
  Runtime : TFLITE
125
+ Estimated inference time (ms) : 26.3
126
+ Estimated peak memory usage (MB): [0, 37]
127
  Total # Ops : 1568
128
  Compute Unit(s) : NPU (1568 ops)
129
  ```
 
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 Swin-Base 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