User | Benchmarker |
Upload Date | March 29 2025 02:29 PM |
Views | 5 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi 24095PCADG |
Model ID | Xiaomi 24095PCADG |
Motherboard | malachite |
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 | 11.16 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
292
54.3 IPS |
|
Image Classification (HP)
|
100% |
279
51.8 IPS |
|
Image Classification (Q)
|
100% |
814
151.5 IPS |
|
Image Segmentation (SP)
|
100% |
339
5.50 IPS |
|
Image Segmentation (HP)
|
100% |
341
5.52 IPS |
|
Image Segmentation (Q)
|
98% |
969
15.8 IPS |
|
Pose Estimation (SP)
|
100% |
1260
1.47 IPS |
|
Pose Estimation (HP)
|
100% |
1272
1.48 IPS |
|
Pose Estimation (Q)
|
84% |
2261
2.68 IPS |
|
Object Detection (SP)
|
100% |
263
20.9 IPS |
|
Object Detection (HP)
|
100% |
265
21.0 IPS |
|
Object Detection (Q)
|
83% |
820
66.2 IPS |
|
Face Detection (SP)
|
100% |
731
8.69 IPS |
|
Face Detection (HP)
|
100% |
735
8.73 IPS |
|
Face Detection (Q)
|
95% |
1984
23.7 IPS |
|
Depth Estimation (SP)
|
100% |
945
7.28 IPS |
|
Depth Estimation (HP)
|
99% |
929
7.16 IPS |
|
Depth Estimation (Q)
|
64% |
1969
18.0 IPS |
|
Style Transfer (SP)
|
89% |
2363
3.07 IPS |
|
Style Transfer (HP)
|
89% |
2289
2.97 IPS |
|
Style Transfer (Q)
|
98% |
5391
6.95 IPS |
|
Image Super-Resolution (SP)
|
100% |
580
21.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
537
19.8 IPS |
|
Image Super-Resolution (Q)
|
97% |
1228
45.5 IPS |
|
Text Classification (SP)
|
100% |
312
416.9 IPS |
|
Text Classification (HP)
|
100% |
315
419.9 IPS |
|
Text Classification (Q)
|
88% |
591
797.4 IPS |
|
Machine Translation (SP)
|
100% |
504
8.68 IPS |
|
Machine Translation (HP)
|
100% |
500
8.62 IPS |
|
Machine Translation (Q)
|
50% |
326
11.6 IPS |