Upload Date | April 01 2025 01:53 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | motorola ThinkPhone 25 by motorola |
Model ID | motorola ThinkPhone 25 by motorola |
Motherboard | vienna |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 4 Cores @ 2.00 GHz |
Cluster 2 | 4 Cores @ 2.50 GHz |
Memory Information | |
---|---|
Size | 7.26 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
186
34.7 IPS |
|
Image Classification (HP)
|
100% |
240
44.7 IPS |
|
Image Classification (Q)
|
99% |
233
43.4 IPS |
|
Image Segmentation (SP)
|
100% |
379
6.14 IPS |
|
Image Segmentation (HP)
|
100% |
437
7.09 IPS |
|
Image Segmentation (Q)
|
98% |
407
6.62 IPS |
|
Pose Estimation (SP)
|
100% |
190
0.22 IPS |
|
Pose Estimation (HP)
|
100% |
253
0.30 IPS |
|
Pose Estimation (Q)
|
96% |
252
0.29 IPS |
|
Object Detection (SP)
|
100% |
151
12.0 IPS |
|
Object Detection (HP)
|
100% |
204
16.2 IPS |
|
Object Detection (Q)
|
83% |
221
17.9 IPS |
|
Face Detection (SP)
|
100% |
699
8.30 IPS |
|
Face Detection (HP)
|
100% |
772
9.18 IPS |
|
Face Detection (Q)
|
97% |
744
8.87 IPS |
|
Depth Estimation (SP)
|
100% |
374
2.88 IPS |
|
Depth Estimation (HP)
|
99% |
471
3.63 IPS |
|
Depth Estimation (Q)
|
62% |
381
3.61 IPS |
|
Style Transfer (SP)
|
100% |
996
1.28 IPS |
|
Style Transfer (HP)
|
100% |
1184
1.52 IPS |
|
Style Transfer (Q)
|
98% |
1176
1.52 IPS |
|
Image Super-Resolution (SP)
|
100% |
196
7.23 IPS |
|
Image Super-Resolution (HP)
|
100% |
235
8.68 IPS |
|
Image Super-Resolution (Q)
|
97% |
221
8.20 IPS |
|
Text Classification (SP)
|
100% |
111
148.0 IPS |
|
Text Classification (HP)
|
100% |
110
147.4 IPS |
|
Text Classification (Q)
|
91% |
288
387.7 IPS |
|
Machine Translation (SP)
|
100% |
182
3.13 IPS |
|
Machine Translation (HP)
|
100% |
182
3.13 IPS |
|
Machine Translation (Q)
|
57% |
214
5.23 IPS |