Upload Date | September 24 2024 05:21 PM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi 2312DRAABC |
Model ID | Xiaomi 2312DRAABC |
Motherboard | gold |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 4 part 3339 revision 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 6 Cores @ 2.00 GHz |
Cluster 2 | 2 Cores @ 2.40 GHz |
Memory Information | |
---|---|
Size | 5.43 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
103
19.1 IPS |
|
Image Classification (HP)
|
100% |
185
34.3 IPS |
|
Image Classification (Q)
|
99% |
178
33.2 IPS |
|
Image Segmentation (SP)
|
100% |
143
2.32 IPS |
|
Image Segmentation (HP)
|
100% |
247
4.01 IPS |
|
Image Segmentation (Q)
|
98% |
238
3.88 IPS |
|
Pose Estimation (SP)
|
100% |
99
0.12 IPS |
|
Pose Estimation (HP)
|
100% |
114
0.13 IPS |
|
Pose Estimation (Q)
|
96% |
113
0.13 IPS |
|
Object Detection (SP)
|
100% |
86
6.83 IPS |
|
Object Detection (HP)
|
100% |
146
11.6 IPS |
|
Object Detection (Q)
|
83% |
134
10.8 IPS |
|
Face Detection (SP)
|
100% |
312
3.71 IPS |
|
Face Detection (HP)
|
100% |
458
5.44 IPS |
|
Face Detection (Q)
|
97% |
432
5.15 IPS |
|
Depth Estimation (SP)
|
100% |
185
1.42 IPS |
|
Depth Estimation (HP)
|
99% |
242
1.86 IPS |
|
Depth Estimation (Q)
|
62% |
196
1.85 IPS |
|
Style Transfer (SP)
|
100% |
375
0.48 IPS |
|
Style Transfer (HP)
|
100% |
518
0.67 IPS |
|
Style Transfer (Q)
|
98% |
516
0.67 IPS |
|
Image Super-Resolution (SP)
|
100% |
96
3.55 IPS |
|
Image Super-Resolution (HP)
|
100% |
148
5.47 IPS |
|
Image Super-Resolution (Q)
|
97% |
147
5.44 IPS |
|
Text Classification (SP)
|
100% |
137
182.4 IPS |
|
Text Classification (HP)
|
100% |
135
180.0 IPS |
|
Text Classification (Q)
|
91% |
227
305.6 IPS |
|
Machine Translation (SP)
|
100% |
229
3.94 IPS |
|
Machine Translation (HP)
|
100% |
228
3.92 IPS |
|
Machine Translation (Q)
|
57% |
182
4.45 IPS |