Hugging Face's logo

qualcomm
/
YOLOv11-Segmentation

Image Segmentation
PyTorch
real_time
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
dd1ed28
·
verified ·
1 Parent(s): 00c9a83

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +24 -20
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  library_name: pytorch
3
- license: agpl-3.0
4
  tags:
5
  - real_time
6
  - android
@@ -23,32 +23,36 @@ This model is an implementation of YOLOv11-Segmentation found [here](https://git
23
 
24
  ### Model Details
25
 
26
- - **Model Type:** Semantic segmentation
27
  - **Model Stats:**
28
  - Model checkpoint: YOLO11N-Seg
29
  - Input resolution: 640x640
30
  - Number of parameters: 2.9M
31
- - Model size: 11.1 MB
32
  - Number of output classes: 80
 
33
 
34
- | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
35
  |---|---|---|---|---|---|---|---|---|
36
- | YOLOv11-Segmentation | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 8.653 ms | 4 - 23 MB | FP16 | NPU | -- |
37
- | YOLOv11-Segmentation | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 115.357 ms | 95 - 104 MB | FP32 | CPU | -- |
38
- | YOLOv11-Segmentation | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 6.283 ms | 0 - 48 MB | FP16 | NPU | -- |
39
- | YOLOv11-Segmentation | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 98.029 ms | 99 - 125 MB | FP32 | CPU | -- |
40
- | YOLOv11-Segmentation | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 5.026 ms | 3 - 47 MB | FP16 | NPU | -- |
41
- | YOLOv11-Segmentation | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 73.514 ms | 108 - 123 MB | FP32 | CPU | -- |
42
- | YOLOv11-Segmentation | SA7255P ADP | SA7255P | TFLITE | 81.898 ms | 4 - 45 MB | FP16 | NPU | -- |
43
- | YOLOv11-Segmentation | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 8.781 ms | 4 - 24 MB | FP16 | NPU | -- |
44
- | YOLOv11-Segmentation | SA8295P ADP | SA8295P | TFLITE | 13.37 ms | 4 - 30 MB | FP16 | NPU | -- |
45
- | YOLOv11-Segmentation | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 8.581 ms | 4 - 25 MB | FP16 | NPU | -- |
46
- | YOLOv11-Segmentation | SA8775P ADP | SA8775P | TFLITE | 12.205 ms | 4 - 44 MB | FP16 | NPU | -- |
47
- | YOLOv11-Segmentation | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 81.898 ms | 4 - 45 MB | FP16 | NPU | -- |
48
- | YOLOv11-Segmentation | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 8.651 ms | 4 - 25 MB | FP16 | NPU | -- |
49
- | YOLOv11-Segmentation | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 12.205 ms | 4 - 44 MB | FP16 | NPU | -- |
50
- | YOLOv11-Segmentation | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 12.372 ms | 4 - 44 MB | FP16 | NPU | -- |
51
- | YOLOv11-Segmentation | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 32.566 ms | 116 - 116 MB | FP32 | CPU | -- |
 
 
 
 
52
 
53
 
54
 
 
1
  ---
2
  library_name: pytorch
3
+ license: other
4
  tags:
5
  - real_time
6
  - android
 
23
 
24
  ### Model Details
25
 
26
+ - **Model Type:** Model_use_case.semantic_segmentation
27
  - **Model Stats:**
28
  - Model checkpoint: YOLO11N-Seg
29
  - Input resolution: 640x640
30
  - Number of parameters: 2.9M
 
31
  - Number of output classes: 80
32
+ - Model size (float): 11.1 MB
33
 
34
+ | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
35
  |---|---|---|---|---|---|---|---|---|
36
+ | YOLOv11-Segmentation | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 20.848 ms | 4 - 43 MB | NPU | -- |
37
+ | YOLOv11-Segmentation | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 12.537 ms | 4 - 39 MB | NPU | -- |
38
+ | YOLOv11-Segmentation | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 8.523 ms | 4 - 23 MB | NPU | -- |
39
+ | YOLOv11-Segmentation | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 10.484 ms | 2 - 41 MB | NPU | -- |
40
+ | YOLOv11-Segmentation | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 20.848 ms | 4 - 43 MB | NPU | -- |
41
+ | YOLOv11-Segmentation | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 8.552 ms | 4 - 22 MB | NPU | -- |
42
+ | YOLOv11-Segmentation | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 13.22 ms | 4 - 30 MB | NPU | -- |
43
+ | YOLOv11-Segmentation | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 8.56 ms | 4 - 23 MB | NPU | -- |
44
+ | YOLOv11-Segmentation | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 10.484 ms | 2 - 41 MB | NPU | -- |
45
+ | YOLOv11-Segmentation | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 8.575 ms | 4 - 23 MB | NPU | -- |
46
+ | YOLOv11-Segmentation | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 114.987 ms | 80 - 94 MB | CPU | -- |
47
+ | YOLOv11-Segmentation | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 6.213 ms | 1 - 49 MB | NPU | -- |
48
+ | YOLOv11-Segmentation | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 84.21 ms | 99 - 127 MB | CPU | -- |
49
+ | YOLOv11-Segmentation | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 5.884 ms | 4 - 47 MB | NPU | -- |
50
+ | YOLOv11-Segmentation | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 73.372 ms | 100 - 114 MB | CPU | -- |
51
+ | YOLOv11-Segmentation | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 37.033 ms | 114 - 114 MB | CPU | -- |
52
+ | YOLOv11-Segmentation | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 172.382 ms | 151 - 157 MB | CPU | -- |
53
+ | YOLOv11-Segmentation | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 115.923 ms | 165 - 190 MB | CPU | -- |
54
+ | YOLOv11-Segmentation | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 113.806 ms | 169 - 187 MB | CPU | -- |
55
+ | YOLOv11-Segmentation | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 58.495 ms | 258 - 258 MB | CPU | -- |
56
 
57
 
58