Upload Date | September 16 2024 11:09 AM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi 2406APNFAG |
Model ID | Xiaomi 2406APNFAG |
Motherboard | degas |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3405 revision 0 |
Base Frequency | 2.20 GHz |
Cluster 1 | 4 Cores @ 2.20 GHz |
Cluster 2 | 3 Cores @ 3.20 GHz |
Cluster 3 | 1 Core @ 3.35 GHz |
Memory Information | |
---|---|
Size | 11.07 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
310
57.7 IPS |
|
Image Classification (HP)
|
100% |
402
74.8 IPS |
|
Image Classification (Q)
|
99% |
324
60.4 IPS |
|
Image Segmentation (SP)
|
100% |
653
10.6 IPS |
|
Image Segmentation (HP)
|
100% |
736
11.9 IPS |
|
Image Segmentation (Q)
|
98% |
721
11.7 IPS |
|
Pose Estimation (SP)
|
100% |
366
0.43 IPS |
|
Pose Estimation (HP)
|
100% |
516
0.60 IPS |
|
Pose Estimation (Q)
|
96% |
513
0.60 IPS |
|
Object Detection (SP)
|
100% |
257
20.4 IPS |
|
Object Detection (HP)
|
100% |
315
25.0 IPS |
|
Object Detection (Q)
|
83% |
331
26.8 IPS |
|
Face Detection (SP)
|
100% |
1168
13.9 IPS |
|
Face Detection (HP)
|
100% |
1308
15.5 IPS |
|
Face Detection (Q)
|
97% |
1234
14.7 IPS |
|
Depth Estimation (SP)
|
100% |
689
5.31 IPS |
|
Depth Estimation (HP)
|
99% |
826
6.37 IPS |
|
Depth Estimation (Q)
|
62% |
668
6.32 IPS |
|
Style Transfer (SP)
|
100% |
1953
2.51 IPS |
|
Style Transfer (HP)
|
100% |
2396
3.08 IPS |
|
Style Transfer (Q)
|
98% |
2383
3.07 IPS |
|
Image Super-Resolution (SP)
|
100% |
359
13.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
420
15.5 IPS |
|
Image Super-Resolution (Q)
|
97% |
419
15.5 IPS |
|
Text Classification (SP)
|
100% |
205
273.5 IPS |
|
Text Classification (HP)
|
100% |
205
273.8 IPS |
|
Text Classification (Q)
|
91% |
354
475.8 IPS |
|
Machine Translation (SP)
|
100% |
334
5.75 IPS |
|
Machine Translation (HP)
|
100% |
338
5.83 IPS |
|
Machine Translation (Q)
|
57% |
282
6.90 IPS |