qaihm-bot commited on
Commit
34eb9d7
·
verified ·
1 Parent(s): 704a723

See https://github.com/quic/ai-hub-models/releases/v0.38.0 for changelog.

Files changed (1) hide show
  1. README.md +47 -52
README.md CHANGED
@@ -38,57 +38,52 @@ More details on model performance across various devices, can be found
38
 
39
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
40
  |---|---|---|---|---|---|---|---|---|
41
- | YOLOv8-Segmentation | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 17.723 ms | 4 - 75 MB | NPU | -- |
42
- | YOLOv8-Segmentation | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 16.601 ms | 5 - 118 MB | NPU | -- |
43
- | YOLOv8-Segmentation | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 8.708 ms | 4 - 52 MB | NPU | -- |
44
- | YOLOv8-Segmentation | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 10.625 ms | 5 - 49 MB | NPU | -- |
45
- | YOLOv8-Segmentation | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 4.871 ms | 0 - 39 MB | NPU | -- |
46
- | YOLOv8-Segmentation | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 4.357 ms | 5 - 25 MB | NPU | -- |
47
- | YOLOv8-Segmentation | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 6.41 ms | 0 - 106 MB | NPU | -- |
48
- | YOLOv8-Segmentation | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 6.686 ms | 4 - 75 MB | NPU | -- |
49
- | YOLOv8-Segmentation | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 6.11 ms | 1 - 112 MB | NPU | -- |
50
- | YOLOv8-Segmentation | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 17.723 ms | 4 - 75 MB | NPU | -- |
51
- | YOLOv8-Segmentation | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 16.601 ms | 5 - 118 MB | NPU | -- |
52
- | YOLOv8-Segmentation | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 4.951 ms | 0 - 38 MB | NPU | -- |
53
- | YOLOv8-Segmentation | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 4.333 ms | 6 - 22 MB | NPU | -- |
54
- | YOLOv8-Segmentation | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 9.889 ms | 4 - 41 MB | NPU | -- |
55
- | YOLOv8-Segmentation | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 8.462 ms | 2 - 36 MB | NPU | -- |
56
- | YOLOv8-Segmentation | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 4.886 ms | 0 - 37 MB | NPU | -- |
57
- | YOLOv8-Segmentation | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 4.355 ms | 5 - 18 MB | NPU | -- |
58
- | YOLOv8-Segmentation | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 6.686 ms | 4 - 75 MB | NPU | -- |
59
- | YOLOv8-Segmentation | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 6.11 ms | 1 - 112 MB | NPU | -- |
60
- | YOLOv8-Segmentation | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 4.906 ms | 0 - 37 MB | NPU | -- |
61
- | YOLOv8-Segmentation | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 4.338 ms | 5 - 27 MB | NPU | -- |
62
- | YOLOv8-Segmentation | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 6.657 ms | 3 - 104 MB | NPU | -- |
63
- | YOLOv8-Segmentation | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 3.644 ms | 0 - 96 MB | NPU | -- |
64
- | YOLOv8-Segmentation | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 3.224 ms | 5 - 204 MB | NPU | -- |
65
- | YOLOv8-Segmentation | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 4.32 ms | 0 - 190 MB | NPU | -- |
66
- | YOLOv8-Segmentation | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 3.475 ms | 3 - 76 MB | NPU | -- |
67
- | YOLOv8-Segmentation | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 2.858 ms | 5 - 129 MB | NPU | -- |
68
- | YOLOv8-Segmentation | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 3.545 ms | 14 - 109 MB | NPU | -- |
69
- | YOLOv8-Segmentation | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 4.749 ms | 93 - 93 MB | NPU | -- |
70
- | YOLOv8-Segmentation | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 6.455 ms | 17 - 17 MB | NPU | -- |
71
- | YOLOv8-Segmentation | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 7.783 ms | 2 - 33 MB | NPU | -- |
72
- | YOLOv8-Segmentation | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 4.76 ms | 2 - 47 MB | NPU | -- |
73
- | YOLOv8-Segmentation | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 3.791 ms | 2 - 13 MB | NPU | -- |
74
- | YOLOv8-Segmentation | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 47.221 ms | 19 - 172 MB | NPU | -- |
75
- | YOLOv8-Segmentation | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 4.412 ms | 2 - 33 MB | NPU | -- |
76
- | YOLOv8-Segmentation | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 16.316 ms | 2 - 38 MB | NPU | -- |
77
- | YOLOv8-Segmentation | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | ONNX | 220.261 ms | 87 - 108 MB | CPU | -- |
78
- | YOLOv8-Segmentation | w8a16 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | ONNX | 187.916 ms | 91 - 97 MB | CPU | -- |
79
- | YOLOv8-Segmentation | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 7.783 ms | 2 - 33 MB | NPU | -- |
80
- | YOLOv8-Segmentation | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 3.801 ms | 2 - 13 MB | NPU | -- |
81
- | YOLOv8-Segmentation | w8a16 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 5.147 ms | 2 - 42 MB | NPU | -- |
82
- | YOLOv8-Segmentation | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 3.82 ms | 2 - 12 MB | NPU | -- |
83
- | YOLOv8-Segmentation | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 4.412 ms | 2 - 33 MB | NPU | -- |
84
- | YOLOv8-Segmentation | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 3.812 ms | 2 - 13 MB | NPU | -- |
85
- | YOLOv8-Segmentation | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 48.642 ms | 27 - 174 MB | NPU | -- |
86
- | YOLOv8-Segmentation | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 2.534 ms | 2 - 43 MB | NPU | -- |
87
- | YOLOv8-Segmentation | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 37.366 ms | 19 - 1509 MB | NPU | -- |
88
- | YOLOv8-Segmentation | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 2.102 ms | 2 - 41 MB | NPU | -- |
89
- | YOLOv8-Segmentation | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 40.583 ms | 17 - 553 MB | NPU | -- |
90
- | YOLOv8-Segmentation | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 4.239 ms | 7 - 7 MB | NPU | -- |
91
- | YOLOv8-Segmentation | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 47.26 ms | 59 - 59 MB | NPU | -- |
92
 
93
 
94
 
@@ -170,7 +165,7 @@ from qai_hub_models.models.yolov8_seg import Model
170
  torch_model = Model.from_pretrained()
171
 
172
  # Device
173
- device = hub.Device("Samsung Galaxy S24")
174
 
175
  # Trace model
176
  input_shape = torch_model.get_input_spec()
 
38
 
39
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
40
  |---|---|---|---|---|---|---|---|---|
41
+ | YOLOv8-Segmentation | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 17.683 ms | 4 - 75 MB | NPU | -- |
42
+ | YOLOv8-Segmentation | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 16.854 ms | 2 - 114 MB | NPU | -- |
43
+ | YOLOv8-Segmentation | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 9.079 ms | 4 - 49 MB | NPU | -- |
44
+ | YOLOv8-Segmentation | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 13.653 ms | 5 - 48 MB | NPU | -- |
45
+ | YOLOv8-Segmentation | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 4.821 ms | 0 - 36 MB | NPU | -- |
46
+ | YOLOv8-Segmentation | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 4.381 ms | 3 - 24 MB | NPU | -- |
47
+ | YOLOv8-Segmentation | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 6.562 ms | 0 - 65 MB | NPU | -- |
48
+ | YOLOv8-Segmentation | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 6.603 ms | 4 - 74 MB | NPU | -- |
49
+ | YOLOv8-Segmentation | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 6.235 ms | 2 - 113 MB | NPU | -- |
50
+ | YOLOv8-Segmentation | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 17.683 ms | 4 - 75 MB | NPU | -- |
51
+ | YOLOv8-Segmentation | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 16.854 ms | 2 - 114 MB | NPU | -- |
52
+ | YOLOv8-Segmentation | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 4.843 ms | 0 - 37 MB | NPU | -- |
53
+ | YOLOv8-Segmentation | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 4.366 ms | 5 - 20 MB | NPU | -- |
54
+ | YOLOv8-Segmentation | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 10.325 ms | 4 - 41 MB | NPU | -- |
55
+ | YOLOv8-Segmentation | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 8.482 ms | 4 - 38 MB | NPU | -- |
56
+ | YOLOv8-Segmentation | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 4.808 ms | 0 - 37 MB | NPU | -- |
57
+ | YOLOv8-Segmentation | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 4.356 ms | 5 - 32 MB | NPU | -- |
58
+ | YOLOv8-Segmentation | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 6.603 ms | 4 - 74 MB | NPU | -- |
59
+ | YOLOv8-Segmentation | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 6.235 ms | 2 - 113 MB | NPU | -- |
60
+ | YOLOv8-Segmentation | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 3.567 ms | 0 - 97 MB | NPU | -- |
61
+ | YOLOv8-Segmentation | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 3.188 ms | 5 - 199 MB | NPU | -- |
62
+ | YOLOv8-Segmentation | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 4.351 ms | 0 - 163 MB | NPU | -- |
63
+ | YOLOv8-Segmentation | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 2.867 ms | 0 - 78 MB | NPU | -- |
64
+ | YOLOv8-Segmentation | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 2.423 ms | 5 - 127 MB | NPU | -- |
65
+ | YOLOv8-Segmentation | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 4.234 ms | 10 - 112 MB | NPU | -- |
66
+ | YOLOv8-Segmentation | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 4.781 ms | 67 - 67 MB | NPU | -- |
67
+ | YOLOv8-Segmentation | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 6.779 ms | 17 - 17 MB | NPU | -- |
68
+ | YOLOv8-Segmentation | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 7.704 ms | 2 - 37 MB | NPU | -- |
69
+ | YOLOv8-Segmentation | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 4.924 ms | 2 - 48 MB | NPU | -- |
70
+ | YOLOv8-Segmentation | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 3.824 ms | 2 - 14 MB | NPU | -- |
71
+ | YOLOv8-Segmentation | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 45.976 ms | 26 - 174 MB | NPU | -- |
72
+ | YOLOv8-Segmentation | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 4.45 ms | 1 - 39 MB | NPU | -- |
73
+ | YOLOv8-Segmentation | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 16.072 ms | 2 - 39 MB | NPU | -- |
74
+ | YOLOv8-Segmentation | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | ONNX | 237.432 ms | 93 - 108 MB | CPU | -- |
75
+ | YOLOv8-Segmentation | w8a16 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | ONNX | 185.128 ms | 91 - 98 MB | CPU | -- |
76
+ | YOLOv8-Segmentation | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 7.704 ms | 2 - 37 MB | NPU | -- |
77
+ | YOLOv8-Segmentation | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 3.834 ms | 2 - 13 MB | NPU | -- |
78
+ | YOLOv8-Segmentation | w8a16 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 5.166 ms | 2 - 43 MB | NPU | -- |
79
+ | YOLOv8-Segmentation | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 3.837 ms | 2 - 14 MB | NPU | -- |
80
+ | YOLOv8-Segmentation | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 4.45 ms | 1 - 39 MB | NPU | -- |
81
+ | YOLOv8-Segmentation | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 2.523 ms | 0 - 47 MB | NPU | -- |
82
+ | YOLOv8-Segmentation | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 36.868 ms | 18 - 1666 MB | NPU | -- |
83
+ | YOLOv8-Segmentation | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 1.769 ms | 2 - 45 MB | NPU | -- |
84
+ | YOLOv8-Segmentation | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 32.565 ms | 40 - 809 MB | NPU | -- |
85
+ | YOLOv8-Segmentation | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 4.286 ms | 8 - 8 MB | NPU | -- |
86
+ | YOLOv8-Segmentation | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 46.242 ms | 58 - 58 MB | NPU | -- |
 
 
 
 
 
87
 
88
 
89
 
 
165
  torch_model = Model.from_pretrained()
166
 
167
  # Device
168
+ device = hub.Device("Samsung Galaxy S25")
169
 
170
  # Trace model
171
  input_shape = torch_model.get_input_spec()