Upload Date | March 13 2025 11:30 AM |
Views | 5 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | samsung SM-E066B |
Model ID | samsung SM-E066B |
Motherboard | a06x |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 4 part 3339 revision 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 6 Cores @ 2.00 GHz |
Cluster 2 | 2 Cores @ 2.40 GHz |
Memory Information | |
---|---|
Size | 3.42 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
232
43.2 IPS |
|
Image Classification (HP)
|
100% |
231
42.9 IPS |
|
Image Classification (Q)
|
100% |
687
127.8 IPS |
|
Image Segmentation (SP)
|
100% |
282
4.57 IPS |
|
Image Segmentation (HP)
|
100% |
282
4.57 IPS |
|
Image Segmentation (Q)
|
98% |
715
11.6 IPS |
|
Pose Estimation (SP)
|
100% |
1053
1.23 IPS |
|
Pose Estimation (HP)
|
100% |
1013
1.18 IPS |
|
Pose Estimation (Q)
|
84% |
1555
1.84 IPS |
|
Object Detection (SP)
|
100% |
223
17.7 IPS |
|
Object Detection (HP)
|
100% |
222
17.6 IPS |
|
Object Detection (Q)
|
83% |
637
51.4 IPS |
|
Face Detection (SP)
|
100% |
722
8.58 IPS |
|
Face Detection (HP)
|
100% |
719
8.54 IPS |
|
Face Detection (Q)
|
95% |
1410
16.8 IPS |
|
Depth Estimation (SP)
|
100% |
903
6.95 IPS |
|
Depth Estimation (HP)
|
99% |
898
6.92 IPS |
|
Depth Estimation (Q)
|
64% |
1437
13.2 IPS |
|
Style Transfer (SP)
|
89% |
1730
2.25 IPS |
|
Style Transfer (HP)
|
89% |
1710
2.22 IPS |
|
Style Transfer (Q)
|
98% |
3560
4.59 IPS |
|
Image Super-Resolution (SP)
|
100% |
453
16.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
449
16.6 IPS |
|
Image Super-Resolution (Q)
|
97% |
857
31.8 IPS |
|
Text Classification (SP)
|
100% |
255
340.0 IPS |
|
Text Classification (HP)
|
100% |
250
333.2 IPS |
|
Text Classification (Q)
|
88% |
455
613.4 IPS |
|
Machine Translation (SP)
|
100% |
444
7.64 IPS |
|
Machine Translation (HP)
|
100% |
442
7.62 IPS |
|
Machine Translation (Q)
|
50% |
316
11.2 IPS |