Upload Date | April 16 2025 06:28 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | QNN |
Device | ARM Qualcomm |
System Information | |
---|---|
Operating System | Android 13 |
Model | LENOVO Lenovo TB-Q706F |
Model ID | LENOVO Lenovo TB-Q706F |
Motherboard | kona |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3341 revision 0 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 3 Cores @ 2.42 GHz |
Cluster 3 | 1 Core @ 3.19 GHz |
Memory Information | |
---|---|
Size | 5.54 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
31
5.86 IPS |
|
Image Classification (HP)
|
100% |
32
5.94 IPS |
|
Image Classification (Q)
|
96% |
1108
206.9 IPS |
|
Image Segmentation (SP)
|
100% |
40
0.66 IPS |
|
Image Segmentation (HP)
|
100% |
41
0.67 IPS |
|
Image Segmentation (Q)
|
98% |
1212
19.7 IPS |
|
Pose Estimation (SP)
|
100% |
60
0.07 IPS |
|
Pose Estimation (HP)
|
100% |
62
0.07 IPS |
|
Pose Estimation (Q)
|
96% |
13275
15.6 IPS |
|
Object Detection (SP)
|
100% |
32
2.53 IPS |
|
Object Detection (HP)
|
100% |
32
2.57 IPS |
|
Object Detection (Q)
|
84% |
1202
97.0 IPS |
|
Face Detection (SP)
|
100% |
77
0.92 IPS |
|
Face Detection (HP)
|
100% |
78
0.93 IPS |
|
Face Detection (Q)
|
97% |
1987
23.7 IPS |
|
Depth Estimation (SP)
|
100% |
76
0.59 IPS |
|
Depth Estimation (HP)
|
99% |
77
0.59 IPS |
|
Depth Estimation (Q)
|
64% |
5348
49.2 IPS |
|
Style Transfer (SP)
|
100% |
132
0.17 IPS |
|
Style Transfer (HP)
|
100% |
132
0.17 IPS |
|
Style Transfer (Q)
|
98% |
18287
23.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
40
1.47 IPS |
|
Image Super-Resolution (HP)
|
100% |
40
1.47 IPS |
|
Image Super-Resolution (Q)
|
97% |
148
5.48 IPS |
|
Text Classification (SP)
|
100% |
56
74.7 IPS |
|
Text Classification (HP)
|
100% |
57
75.6 IPS |
|
Text Classification (Q)
|
93% |
314
421.4 IPS |
|
Machine Translation (SP)
|
100% |
85
1.46 IPS |
|
Machine Translation (HP)
|
100% |
85
1.46 IPS |
|
Machine Translation (Q)
|
0% |
0
1.99 IPS |