Upload Date | April 08 2025 09:36 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | LENOVO TB373FU |
Model ID | LENOVO TB373FU |
Motherboard | P98300DA1 |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3405 revision 0 |
Base Frequency | 2.20 GHz |
Cluster 1 | 4 Cores @ 2.20 GHz |
Cluster 2 | 3 Cores @ 3.20 GHz |
Cluster 3 | 1 Core @ 3.35 GHz |
Memory Information | |
---|---|
Size | 11.42 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
553
102.8 IPS |
|
Image Classification (HP)
|
100% |
699
129.9 IPS |
|
Image Classification (Q)
|
99% |
685
127.8 IPS |
|
Image Segmentation (SP)
|
100% |
1032
16.7 IPS |
|
Image Segmentation (HP)
|
100% |
1134
18.4 IPS |
|
Image Segmentation (Q)
|
98% |
1053
17.1 IPS |
|
Pose Estimation (SP)
|
100% |
585
0.68 IPS |
|
Pose Estimation (HP)
|
100% |
810
0.95 IPS |
|
Pose Estimation (Q)
|
96% |
805
0.94 IPS |
|
Object Detection (SP)
|
100% |
417
33.1 IPS |
|
Object Detection (HP)
|
100% |
465
36.9 IPS |
|
Object Detection (Q)
|
83% |
508
41.1 IPS |
|
Face Detection (SP)
|
100% |
1847
21.9 IPS |
|
Face Detection (HP)
|
100% |
2137
25.4 IPS |
|
Face Detection (Q)
|
97% |
1783
21.3 IPS |
|
Depth Estimation (SP)
|
100% |
1051
8.10 IPS |
|
Depth Estimation (HP)
|
99% |
1313
10.1 IPS |
|
Depth Estimation (Q)
|
62% |
1024
9.70 IPS |
|
Style Transfer (SP)
|
100% |
3070
3.95 IPS |
|
Style Transfer (HP)
|
100% |
3743
4.81 IPS |
|
Style Transfer (Q)
|
98% |
3716
4.79 IPS |
|
Image Super-Resolution (SP)
|
100% |
552
20.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
612
22.6 IPS |
|
Image Super-Resolution (Q)
|
97% |
601
22.3 IPS |
|
Text Classification (SP)
|
100% |
233
310.9 IPS |
|
Text Classification (HP)
|
100% |
236
314.9 IPS |
|
Text Classification (Q)
|
91% |
406
546.4 IPS |
|
Machine Translation (SP)
|
100% |
396
6.82 IPS |
|
Machine Translation (HP)
|
100% |
397
6.84 IPS |
|
Machine Translation (Q)
|
57% |
304
7.43 IPS |