User | Vaitek |
Upload Date | October 09 2024 02:08 PM |
Views | 4 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 13 |
Model | Xiaomi 23073RPBFC |
Model ID | Xiaomi 23073RPBFC |
Motherboard | bengal |
Governor | walt |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3337 revision 0 |
Base Frequency | 1.90 GHz |
Cluster 1 | 4 Cores @ 1.90 GHz |
Cluster 2 | 4 Cores @ 2.40 GHz |
Memory Information | |
---|---|
Size | 5.56 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
174
32.3 IPS |
|
Image Classification (HP)
|
100% |
175
32.6 IPS |
|
Image Classification (Q)
|
100% |
318
59.0 IPS |
|
Image Segmentation (SP)
|
100% |
215
3.49 IPS |
|
Image Segmentation (HP)
|
100% |
214
3.47 IPS |
|
Image Segmentation (Q)
|
98% |
398
6.47 IPS |
|
Pose Estimation (SP)
|
100% |
838
0.98 IPS |
|
Pose Estimation (HP)
|
100% |
830
0.97 IPS |
|
Pose Estimation (Q)
|
84% |
691
0.82 IPS |
|
Object Detection (SP)
|
100% |
167
13.3 IPS |
|
Object Detection (HP)
|
100% |
167
13.3 IPS |
|
Object Detection (Q)
|
83% |
317
25.6 IPS |
|
Face Detection (SP)
|
100% |
476
5.66 IPS |
|
Face Detection (HP)
|
100% |
470
5.58 IPS |
|
Face Detection (Q)
|
95% |
733
8.75 IPS |
|
Depth Estimation (SP)
|
100% |
496
3.82 IPS |
|
Depth Estimation (HP)
|
99% |
644
4.96 IPS |
|
Depth Estimation (Q)
|
64% |
741
6.79 IPS |
|
Style Transfer (SP)
|
89% |
1448
1.88 IPS |
|
Style Transfer (HP)
|
89% |
1191
1.55 IPS |
|
Style Transfer (Q)
|
98% |
1181
1.52 IPS |
|
Image Super-Resolution (SP)
|
100% |
355
13.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
360
13.3 IPS |
|
Image Super-Resolution (Q)
|
97% |
200
7.42 IPS |
|
Text Classification (SP)
|
100% |
131
175.4 IPS |
|
Text Classification (HP)
|
100% |
131
174.9 IPS |
|
Text Classification (Q)
|
88% |
144
194.2 IPS |
|
Machine Translation (SP)
|
100% |
212
3.66 IPS |
|
Machine Translation (HP)
|
100% |
205
3.54 IPS |
|
Machine Translation (Q)
|
50% |
99
3.51 IPS |