Upload Date | December 24 2024 12:00 AM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-X916B |
Model ID | samsung SM-X916B |
Motherboard | kalama |
Governor | walt |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3406 revision 0 |
Base Frequency | 2.02 GHz |
Cluster 1 | 3 Cores @ 2.02 GHz |
Cluster 2 | 4 Cores @ 2.80 GHz |
Cluster 3 | 1 Core @ 3.36 GHz |
Memory Information | |
---|---|
Size | 10.91 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
705
131.1 IPS |
|
Image Classification (HP)
|
100% |
560
104.2 IPS |
|
Image Classification (Q)
|
100% |
1300
241.8 IPS |
|
Image Segmentation (SP)
|
100% |
1744
28.3 IPS |
|
Image Segmentation (HP)
|
100% |
496
8.04 IPS |
|
Image Segmentation (Q)
|
98% |
2217
36.0 IPS |
|
Pose Estimation (SP)
|
100% |
1855
2.16 IPS |
|
Pose Estimation (HP)
|
100% |
2090
2.44 IPS |
|
Pose Estimation (Q)
|
84% |
3677
4.36 IPS |
|
Object Detection (SP)
|
98% |
766
61.0 IPS |
|
Object Detection (HP)
|
98% |
704
56.0 IPS |
|
Object Detection (Q)
|
83% |
1044
84.3 IPS |
|
Face Detection (SP)
|
100% |
1330
15.8 IPS |
|
Face Detection (HP)
|
100% |
1334
15.9 IPS |
|
Face Detection (Q)
|
95% |
2163
25.8 IPS |
|
Depth Estimation (SP)
|
99% |
1781
13.8 IPS |
|
Depth Estimation (HP)
|
99% |
1749
13.5 IPS |
|
Depth Estimation (Q)
|
64% |
2416
22.1 IPS |
|
Style Transfer (SP)
|
89% |
3645
4.73 IPS |
|
Style Transfer (HP)
|
89% |
3518
4.57 IPS |
|
Style Transfer (Q)
|
98% |
6212
8.01 IPS |
|
Image Super-Resolution (SP)
|
100% |
676
25.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
667
24.6 IPS |
|
Image Super-Resolution (Q)
|
97% |
1790
66.3 IPS |
|
Text Classification (SP)
|
100% |
310
414.2 IPS |
|
Text Classification (HP)
|
99% |
343
457.7 IPS |
|
Text Classification (Q)
|
88% |
752
1.01 KIPS |
|
Machine Translation (SP)
|
100% |
824
14.2 IPS |
|
Machine Translation (HP)
|
100% |
891
15.3 IPS |
|
Machine Translation (Q)
|
50% |
463
16.4 IPS |