Hugging Face's logo

qualcomm
/
Unet-Segmentation

Image Segmentation
PyTorch
LiteRT
backbone
real_time
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
475b04e
·
verified ·
1 Parent(s): d3efc9c

v0.30.5

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.30.5 for changelog.

Files changed (1) hide show
  1. README.md +33 -33
README.md CHANGED
@@ -37,35 +37,35 @@ More details on model performance across various devices, can be found
37
 
38
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
39
  |---|---|---|---|---|---|---|---|---|
40
- | Unet-Segmentation | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 959.843 ms | 6 - 91 MB | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
41
- | Unet-Segmentation | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 952.991 ms | 3 - 12 MB | NPU | Use Export Script |
42
- | Unet-Segmentation | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 296.461 ms | 6 - 151 MB | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
43
- | Unet-Segmentation | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 304.347 ms | 9 - 115 MB | NPU | Use Export Script |
44
- | Unet-Segmentation | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 164.488 ms | 6 - 466 MB | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
45
- | Unet-Segmentation | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 149.725 ms | 9 - 12 MB | NPU | Use Export Script |
46
- | Unet-Segmentation | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 258.58 ms | 6 - 91 MB | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
47
- | Unet-Segmentation | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 253.903 ms | 1 - 13 MB | NPU | Use Export Script |
48
- | Unet-Segmentation | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 959.843 ms | 6 - 91 MB | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
49
- | Unet-Segmentation | float | SA7255P ADP | Qualcomm® SA7255P | QNN | 952.991 ms | 3 - 12 MB | NPU | Use Export Script |
50
- | Unet-Segmentation | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 166.075 ms | 7 - 464 MB | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
51
- | Unet-Segmentation | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 151.146 ms | 9 - 12 MB | NPU | Use Export Script |
52
- | Unet-Segmentation | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 286.555 ms | 6 - 93 MB | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
53
- | Unet-Segmentation | float | SA8295P ADP | Qualcomm® SA8295P | QNN | 277.519 ms | 0 - 18 MB | NPU | Use Export Script |
54
- | Unet-Segmentation | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 161.89 ms | 6 - 467 MB | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
55
- | Unet-Segmentation | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 151.716 ms | 10 - 12 MB | NPU | Use Export Script |
56
- | Unet-Segmentation | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 258.58 ms | 6 - 91 MB | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
57
- | Unet-Segmentation | float | SA8775P ADP | Qualcomm® SA8775P | QNN | 253.903 ms | 1 - 13 MB | NPU | Use Export Script |
58
- | Unet-Segmentation | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 161.485 ms | 6 - 464 MB | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
59
- | Unet-Segmentation | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 149.142 ms | 10 - 47 MB | NPU | Use Export Script |
60
- | Unet-Segmentation | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 157.746 ms | 13 - 157 MB | NPU | [Unet-Segmentation.onnx](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.onnx) |
61
- | Unet-Segmentation | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 121.298 ms | 5 - 131 MB | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
62
- | Unet-Segmentation | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 116.077 ms | 9 - 106 MB | NPU | Use Export Script |
63
- | Unet-Segmentation | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 121.388 ms | 21 - 115 MB | NPU | [Unet-Segmentation.onnx](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.onnx) |
64
- | Unet-Segmentation | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 98.008 ms | 6 - 94 MB | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
65
- | Unet-Segmentation | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 106.393 ms | 9 - 109 MB | NPU | Use Export Script |
66
- | Unet-Segmentation | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 110.255 ms | 21 - 113 MB | NPU | [Unet-Segmentation.onnx](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.onnx) |
67
- | Unet-Segmentation | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 145.556 ms | 9 - 9 MB | NPU | Use Export Script |
68
- | Unet-Segmentation | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 153.052 ms | 54 - 54 MB | NPU | [Unet-Segmentation.onnx](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.onnx) |
69
 
70
 
71
 
@@ -129,8 +129,8 @@ Profiling Results
129
  Unet-Segmentation
130
  Device : cs_8275 (ANDROID 14)
131
  Runtime : TFLITE
132
- Estimated inference time (ms) : 959.8
133
- Estimated peak memory usage (MB): [6, 91]
134
  Total # Ops : 32
135
  Compute Unit(s) : npu (32 ops) gpu (0 ops) cpu (0 ops)
136
  ```
@@ -219,13 +219,13 @@ AI Hub. [Sign up for access](https://myaccount.qualcomm.com/signup).
219
  You can also run the demo on-device.
220
 
221
  ```bash
222
- python -m qai_hub_models.models.unet_segmentation.demo --on-device
223
  ```
224
 
225
  **NOTE**: If you want running in a Jupyter Notebook or Google Colab like
226
  environment, please add the following to your cell (instead of the above).
227
  ```
228
- %run -m qai_hub_models.models.unet_segmentation.demo -- --on-device
229
  ```
230
 
231
 
 
37
 
38
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
39
  |---|---|---|---|---|---|---|---|---|
40
+ | Unet-Segmentation | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 7311.581 ms | 2 - 100 MB | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
41
+ | Unet-Segmentation | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 7304.677 ms | 5 - 14 MB | NPU | Use Export Script |
42
+ | Unet-Segmentation | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 262.045 ms | 6 - 161 MB | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
43
+ | Unet-Segmentation | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 279.629 ms | 9 - 127 MB | NPU | Use Export Script |
44
+ | Unet-Segmentation | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 156.435 ms | 6 - 473 MB | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
45
+ | Unet-Segmentation | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 145.707 ms | 10 - 12 MB | NPU | Use Export Script |
46
+ | Unet-Segmentation | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 253.292 ms | 6 - 104 MB | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
47
+ | Unet-Segmentation | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 249.863 ms | 0 - 10 MB | NPU | Use Export Script |
48
+ | Unet-Segmentation | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 7311.581 ms | 2 - 100 MB | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
49
+ | Unet-Segmentation | float | SA7255P ADP | Qualcomm® SA7255P | QNN | 7304.677 ms | 5 - 14 MB | NPU | Use Export Script |
50
+ | Unet-Segmentation | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 157.63 ms | 6 - 464 MB | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
51
+ | Unet-Segmentation | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 148.174 ms | 10 - 12 MB | NPU | Use Export Script |
52
+ | Unet-Segmentation | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 280.587 ms | 4 - 105 MB | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
53
+ | Unet-Segmentation | float | SA8295P ADP | Qualcomm® SA8295P | QNN | 276.216 ms | 0 - 17 MB | NPU | Use Export Script |
54
+ | Unet-Segmentation | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 161.71 ms | 6 - 464 MB | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
55
+ | Unet-Segmentation | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 147.53 ms | 10 - 11 MB | NPU | Use Export Script |
56
+ | Unet-Segmentation | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 253.292 ms | 6 - 104 MB | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
57
+ | Unet-Segmentation | float | SA8775P ADP | Qualcomm® SA8775P | QNN | 249.863 ms | 0 - 10 MB | NPU | Use Export Script |
58
+ | Unet-Segmentation | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 166.244 ms | 3 - 468 MB | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
59
+ | Unet-Segmentation | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 148.565 ms | 9 - 54 MB | NPU | Use Export Script |
60
+ | Unet-Segmentation | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 161.453 ms | 13 - 219 MB | NPU | [Unet-Segmentation.onnx](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.onnx) |
61
+ | Unet-Segmentation | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 114.828 ms | 5 - 144 MB | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
62
+ | Unet-Segmentation | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 113.855 ms | 9 - 115 MB | NPU | Use Export Script |
63
+ | Unet-Segmentation | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 118.472 ms | 21 - 124 MB | NPU | [Unet-Segmentation.onnx](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.onnx) |
64
+ | Unet-Segmentation | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 107.383 ms | 6 - 106 MB | NPU | [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) |
65
+ | Unet-Segmentation | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 94.069 ms | 9 - 126 MB | NPU | Use Export Script |
66
+ | Unet-Segmentation | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 109.082 ms | 21 - 128 MB | NPU | [Unet-Segmentation.onnx](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.onnx) |
67
+ | Unet-Segmentation | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 142.445 ms | 9 - 9 MB | NPU | Use Export Script |
68
+ | Unet-Segmentation | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 151.215 ms | 53 - 53 MB | NPU | [Unet-Segmentation.onnx](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.onnx) |
69
 
70
 
71
 
 
129
  Unet-Segmentation
130
  Device : cs_8275 (ANDROID 14)
131
  Runtime : TFLITE
132
+ Estimated inference time (ms) : 7311.6
133
+ Estimated peak memory usage (MB): [2, 100]
134
  Total # Ops : 32
135
  Compute Unit(s) : npu (32 ops) gpu (0 ops) cpu (0 ops)
136
  ```
 
219
  You can also run the demo on-device.
220
 
221
  ```bash
222
+ python -m qai_hub_models.models.unet_segmentation.demo --eval-mode on-device
223
  ```
224
 
225
  **NOTE**: If you want running in a Jupyter Notebook or Google Colab like
226
  environment, please add the following to your cell (instead of the above).
227
  ```
228
+ %run -m qai_hub_models.models.unet_segmentation.demo -- --eval-mode on-device
229
  ```
230
 
231