Hugging Face's logo

qualcomm
/
Unet-Segmentation

Image Segmentation
PyTorch
TF Lite
ONNX
backbone
real_time
android
Model card Files Community
qaihm-bot commited on
Commit
b9a4901
·
verified ·
1 Parent(s): 27e8fbf

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +31 -30
README.md CHANGED
@@ -37,39 +37,39 @@ More details on model performance across various devices, can be found
37
 
38
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
39
  |---|---|---|---|---|---|---|---|---|
40
- | Unet-Segmentation | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 164.622 ms | 6 - 122 MB | FP16 | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
41
- | Unet-Segmentation | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 153.909 ms | 9 - 39 MB | FP16 | NPU | [Unet-Segmentation.so](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.so) |
42
- | Unet-Segmentation | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 154.921 ms | 13 - 268 MB | FP16 | NPU | [Unet-Segmentation.onnx](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.onnx) |
43
- | Unet-Segmentation | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 112.634 ms | 6 - 94 MB | FP16 | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
44
- | Unet-Segmentation | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 115.254 ms | 9 - 92 MB | FP16 | NPU | [Unet-Segmentation.so](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.so) |
45
- | Unet-Segmentation | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 115.704 ms | 21 - 113 MB | FP16 | NPU | [Unet-Segmentation.onnx](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.onnx) |
46
- | Unet-Segmentation | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 102.79 ms | 5 - 106 MB | FP16 | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
47
- | Unet-Segmentation | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 103.025 ms | 11 - 113 MB | FP16 | NPU | Use Export Script |
48
- | Unet-Segmentation | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 90.395 ms | 23 - 132 MB | FP16 | NPU | [Unet-Segmentation.onnx](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.onnx) |
49
- | Unet-Segmentation | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 163.296 ms | 6 - 242 MB | FP16 | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
50
- | Unet-Segmentation | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 145.364 ms | 10 - 12 MB | FP16 | NPU | Use Export Script |
51
- | Unet-Segmentation | SA7255P ADP | SA7255P | TFLITE | 7406.859 ms | 1 - 99 MB | FP16 | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
52
- | Unet-Segmentation | SA7255P ADP | SA7255P | QNN | 7399.931 ms | 1 - 11 MB | FP16 | NPU | Use Export Script |
53
- | Unet-Segmentation | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 158.779 ms | 6 - 473 MB | FP16 | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
54
- | Unet-Segmentation | SA8255 (Proxy) | SA8255P Proxy | QNN | 144.433 ms | 10 - 12 MB | FP16 | NPU | Use Export Script |
55
- | Unet-Segmentation | SA8295P ADP | SA8295P | TFLITE | 273.56 ms | 6 - 107 MB | FP16 | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
56
- | Unet-Segmentation | SA8295P ADP | SA8295P | QNN | 266.114 ms | 0 - 15 MB | FP16 | NPU | Use Export Script |
57
- | Unet-Segmentation | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 157.966 ms | 6 - 475 MB | FP16 | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
58
- | Unet-Segmentation | SA8650 (Proxy) | SA8650P Proxy | QNN | 142.712 ms | 12 - 14 MB | FP16 | NPU | Use Export Script |
59
- | Unet-Segmentation | SA8775P ADP | SA8775P | TFLITE | 303.225 ms | 6 - 104 MB | FP16 | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
60
- | Unet-Segmentation | SA8775P ADP | SA8775P | QNN | 297.909 ms | 0 - 10 MB | FP16 | NPU | Use Export Script |
61
- | Unet-Segmentation | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 284.441 ms | 6 - 95 MB | FP16 | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
62
- | Unet-Segmentation | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 280.869 ms | 8 - 97 MB | FP16 | NPU | Use Export Script |
63
- | Unet-Segmentation | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 135.781 ms | 9 - 9 MB | FP16 | NPU | Use Export Script |
64
- | Unet-Segmentation | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 147.007 ms | 54 - 54 MB | FP16 | NPU | [Unet-Segmentation.onnx](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.onnx) |
65
 
66
 
67
 
68
 
69
  ## Installation
70
 
71
- This model can be installed as a Python package via pip.
72
 
 
73
  ```bash
74
  pip install qai-hub-models
75
  ```
@@ -125,8 +125,8 @@ Profiling Results
125
  Unet-Segmentation
126
  Device : Samsung Galaxy S23 (13)
127
  Runtime : TFLITE
128
- Estimated inference time (ms) : 164.6
129
- Estimated peak memory usage (MB): [6, 122]
130
  Total # Ops : 32
131
  Compute Unit(s) : NPU (32 ops)
132
  ```
@@ -153,7 +153,7 @@ from qai_hub_models.models.unet_segmentation import Model
153
  torch_model = Model.from_pretrained()
154
 
155
  # Device
156
- device = hub.Device("Samsung Galaxy S23")
157
 
158
  # Trace model
159
  input_shape = torch_model.get_input_spec()
@@ -245,7 +245,8 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
245
 
246
 
247
  ## License
248
- * The license for the original implementation of Unet-Segmentation can be found [here](https://github.com/milesial/Pytorch-UNet/blob/master/LICENSE).
 
249
  * The license for the compiled assets for on-device deployment can be found [here](https://github.com/milesial/Pytorch-UNet/blob/master/LICENSE)
250
 
251
 
 
37
 
38
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
39
  |---|---|---|---|---|---|---|---|---|
40
+ | Unet-Segmentation | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 150.589 ms | 6 - 471 MB | FP16 | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
41
+ | Unet-Segmentation | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 145.477 ms | 10 - 34 MB | FP16 | NPU | [Unet-Segmentation.so](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.so) |
42
+ | Unet-Segmentation | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 159.383 ms | 12 - 147 MB | FP16 | NPU | [Unet-Segmentation.onnx](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.onnx) |
43
+ | Unet-Segmentation | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 114.876 ms | 4 - 91 MB | FP16 | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
44
+ | Unet-Segmentation | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 110.798 ms | 190 - 273 MB | FP16 | NPU | [Unet-Segmentation.so](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.so) |
45
+ | Unet-Segmentation | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 115.502 ms | 65 - 158 MB | FP16 | NPU | [Unet-Segmentation.onnx](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.onnx) |
46
+ | Unet-Segmentation | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 103.261 ms | 6 - 108 MB | FP16 | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
47
+ | Unet-Segmentation | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 103.316 ms | 9 - 111 MB | FP16 | NPU | Use Export Script |
48
+ | Unet-Segmentation | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 92.909 ms | 23 - 131 MB | FP16 | NPU | [Unet-Segmentation.onnx](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.onnx) |
49
+ | Unet-Segmentation | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 157.35 ms | 6 - 120 MB | FP16 | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
50
+ | Unet-Segmentation | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 148.092 ms | 10 - 12 MB | FP16 | NPU | Use Export Script |
51
+ | Unet-Segmentation | SA7255P ADP | SA7255P | TFLITE | 7407.448 ms | 2 - 99 MB | FP16 | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
52
+ | Unet-Segmentation | SA7255P ADP | SA7255P | QNN | 7399.837 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
53
+ | Unet-Segmentation | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 160.985 ms | 5 - 232 MB | FP16 | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
54
+ | Unet-Segmentation | SA8255 (Proxy) | SA8255P Proxy | QNN | 142.971 ms | 9 - 12 MB | FP16 | NPU | Use Export Script |
55
+ | Unet-Segmentation | SA8295P ADP | SA8295P | TFLITE | 273.532 ms | 6 - 106 MB | FP16 | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
56
+ | Unet-Segmentation | SA8295P ADP | SA8295P | QNN | 266.162 ms | 0 - 15 MB | FP16 | NPU | Use Export Script |
57
+ | Unet-Segmentation | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 151.188 ms | 6 - 469 MB | FP16 | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
58
+ | Unet-Segmentation | SA8650 (Proxy) | SA8650P Proxy | QNN | 138.876 ms | 10 - 12 MB | FP16 | NPU | Use Export Script |
59
+ | Unet-Segmentation | SA8775P ADP | SA8775P | TFLITE | 303.256 ms | 6 - 104 MB | FP16 | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
60
+ | Unet-Segmentation | SA8775P ADP | SA8775P | QNN | 297.867 ms | 1 - 11 MB | FP16 | NPU | Use Export Script |
61
+ | Unet-Segmentation | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 279.615 ms | 6 - 94 MB | FP16 | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
62
+ | Unet-Segmentation | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 286.728 ms | 3 - 92 MB | FP16 | NPU | Use Export Script |
63
+ | Unet-Segmentation | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 135.697 ms | 9 - 9 MB | FP16 | NPU | Use Export Script |
64
+ | Unet-Segmentation | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 147.415 ms | 54 - 54 MB | FP16 | NPU | [Unet-Segmentation.onnx](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.onnx) |
65
 
66
 
67
 
68
 
69
  ## Installation
70
 
 
71
 
72
+ Install the package via pip:
73
  ```bash
74
  pip install qai-hub-models
75
  ```
 
125
  Unet-Segmentation
126
  Device : Samsung Galaxy S23 (13)
127
  Runtime : TFLITE
128
+ Estimated inference time (ms) : 150.6
129
+ Estimated peak memory usage (MB): [6, 471]
130
  Total # Ops : 32
131
  Compute Unit(s) : NPU (32 ops)
132
  ```
 
153
  torch_model = Model.from_pretrained()
154
 
155
  # Device
156
+ device = hub.Device("Samsung Galaxy S24")
157
 
158
  # Trace model
159
  input_shape = torch_model.get_input_spec()
 
245
 
246
 
247
  ## License
248
+ * The license for the original implementation of Unet-Segmentation can be found
249
+ [here](https://github.com/milesial/Pytorch-UNet/blob/master/LICENSE).
250
  * The license for the compiled assets for on-device deployment can be found [here](https://github.com/milesial/Pytorch-UNet/blob/master/LICENSE)
251
 
252