User | aeonsim |
Upload Date | November 18 2024 07:19 AM |
Views | 7 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-X210 |
Model ID | samsung SM-X210 |
Motherboard | holi |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 1 |
Base Frequency | 1.80 GHz |
Cluster 1 | 6 Cores @ 1.80 GHz |
Cluster 2 | 2 Cores @ 2.21 GHz |
Memory Information | |
---|---|
Size | 7.21 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
242
45.1 IPS |
|
Image Classification (HP)
|
100% |
242
45.0 IPS |
|
Image Classification (Q)
|
100% |
729
135.6 IPS |
|
Image Segmentation (SP)
|
100% |
317
5.13 IPS |
|
Image Segmentation (HP)
|
100% |
313
5.08 IPS |
|
Image Segmentation (Q)
|
98% |
828
13.5 IPS |
|
Pose Estimation (SP)
|
100% |
1182
1.38 IPS |
|
Pose Estimation (HP)
|
100% |
1161
1.35 IPS |
|
Pose Estimation (Q)
|
84% |
1729
2.05 IPS |
|
Object Detection (SP)
|
100% |
233
18.5 IPS |
|
Object Detection (HP)
|
100% |
234
18.5 IPS |
|
Object Detection (Q)
|
83% |
715
57.8 IPS |
|
Face Detection (SP)
|
100% |
773
9.18 IPS |
|
Face Detection (HP)
|
100% |
765
9.09 IPS |
|
Face Detection (Q)
|
95% |
1721
20.5 IPS |
|
Depth Estimation (SP)
|
100% |
990
7.63 IPS |
|
Depth Estimation (HP)
|
99% |
1019
7.85 IPS |
|
Depth Estimation (Q)
|
64% |
1616
14.8 IPS |
|
Style Transfer (SP)
|
89% |
1943
2.52 IPS |
|
Style Transfer (HP)
|
89% |
1959
2.54 IPS |
|
Style Transfer (Q)
|
98% |
3998
5.16 IPS |
|
Image Super-Resolution (SP)
|
100% |
529
19.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
526
19.4 IPS |
|
Image Super-Resolution (Q)
|
97% |
1008
37.4 IPS |
|
Text Classification (SP)
|
100% |
292
390.3 IPS |
|
Text Classification (HP)
|
100% |
289
385.8 IPS |
|
Text Classification (Q)
|
88% |
584
787.2 IPS |
|
Machine Translation (SP)
|
100% |
484
8.34 IPS |
|
Machine Translation (HP)
|
100% |
482
8.31 IPS |
|
Machine Translation (Q)
|
50% |
380
13.5 IPS |