User | harsidh |
Upload Date | July 06 2025 09:23 AM |
Views | 6 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | samsung SM-X610 |
Model ID | samsung SM-X610 |
Motherboard | s5e8835 |
Governor | energy_aware |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 1 |
Base Frequency | 2.00 GHz |
Cluster 1 | 4 Cores @ 2.00 GHz |
Cluster 2 | 4 Cores @ 2.40 GHz |
Memory Information | |
---|---|
Size | 7.54 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
125
23.2 IPS |
|
Image Classification (HP)
|
100% |
111
20.6 IPS |
|
Image Classification (Q)
|
99% |
274
51.1 IPS |
|
Image Segmentation (SP)
|
100% |
309
5.00 IPS |
|
Image Segmentation (HP)
|
100% |
446
7.23 IPS |
|
Image Segmentation (Q)
|
98% |
376
6.11 IPS |
|
Pose Estimation (SP)
|
100% |
84
0.10 IPS |
|
Pose Estimation (HP)
|
99% |
2470
2.88 IPS |
|
Pose Estimation (Q)
|
98% |
881
1.03 IPS |
|
Object Detection (SP)
|
100% |
125
9.95 IPS |
|
Object Detection (HP)
|
100% |
126
9.98 IPS |
|
Object Detection (Q)
|
87% |
364
29.2 IPS |
|
Face Detection (SP)
|
100% |
324
3.85 IPS |
|
Face Detection (HP)
|
100% |
327
3.88 IPS |
|
Face Detection (Q)
|
97% |
733
8.74 IPS |
|
Depth Estimation (SP)
|
100% |
277
2.13 IPS |
|
Depth Estimation (HP)
|
99% |
277
2.14 IPS |
|
Depth Estimation (Q)
|
64% |
680
6.17 IPS |
|
Style Transfer (SP)
|
100% |
479
0.62 IPS |
|
Style Transfer (HP)
|
100% |
479
0.62 IPS |
|
Style Transfer (Q)
|
98% |
1330
1.72 IPS |
|
Image Super-Resolution (SP)
|
100% |
68
2.52 IPS |
|
Image Super-Resolution (HP)
|
100% |
856
31.6 IPS |
|
Image Super-Resolution (Q)
|
97% |
483
17.9 IPS |
|
Text Classification (SP)
|
100% |
180
240.5 IPS |
|
Text Classification (HP)
|
100% |
180
240.0 IPS |
|
Text Classification (Q)
|
91% |
344
462.8 IPS |
|
Machine Translation (SP)
|
100% |
305
5.25 IPS |
|
Machine Translation (HP)
|
100% |
305
5.26 IPS |
|
Machine Translation (Q)
|
57% |
285
6.97 IPS |