User | LinFengJun |
Upload Date | October 20 2024 01:56 AM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | MediaTek Helio G80 |
System Information | |
---|---|
Operating System | Android 12 |
Model | Xiaomi Redmi 9 |
Model ID | Xiaomi M2004J19C |
Motherboard | lancelot |
CPU Information | |
---|---|
Name | ARM MT6769T |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 3 part 3338 revision 1 |
Base Frequency | 1.80 GHz |
Cluster 1 | 6 Cores @ 1.80 GHz |
Cluster 2 | 2 Cores @ 2.00 GHz |
Memory Information | |
---|---|
Size | 3.61 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
97
18.0 IPS |
|
Image Classification (HP)
|
100% |
100
18.6 IPS |
|
Image Classification (Q)
|
100% |
197
36.6 IPS |
|
Image Segmentation (SP)
|
100% |
116
1.88 IPS |
|
Image Segmentation (HP)
|
100% |
118
1.91 IPS |
|
Image Segmentation (Q)
|
98% |
260
4.23 IPS |
|
Pose Estimation (SP)
|
100% |
469
0.55 IPS |
|
Pose Estimation (HP)
|
100% |
475
0.55 IPS |
|
Pose Estimation (Q)
|
84% |
397
0.47 IPS |
|
Object Detection (SP)
|
100% |
92
7.32 IPS |
|
Object Detection (HP)
|
100% |
94
7.46 IPS |
|
Object Detection (Q)
|
83% |
205
16.5 IPS |
|
Face Detection (SP)
|
100% |
296
3.52 IPS |
|
Face Detection (HP)
|
100% |
294
3.50 IPS |
|
Face Detection (Q)
|
95% |
569
6.80 IPS |
|
Depth Estimation (SP)
|
100% |
402
3.10 IPS |
|
Depth Estimation (HP)
|
99% |
406
3.13 IPS |
|
Depth Estimation (Q)
|
64% |
457
4.19 IPS |
|
Style Transfer (SP)
|
89% |
804
1.04 IPS |
|
Style Transfer (HP)
|
89% |
814
1.06 IPS |
|
Style Transfer (Q)
|
98% |
1049
1.35 IPS |
|
Image Super-Resolution (SP)
|
100% |
198
7.32 IPS |
|
Image Super-Resolution (HP)
|
100% |
199
7.34 IPS |
|
Image Super-Resolution (Q)
|
97% |
256
9.47 IPS |
|
Text Classification (SP)
|
100% |
121
161.2 IPS |
|
Text Classification (HP)
|
100% |
125
166.5 IPS |
|
Text Classification (Q)
|
88% |
205
275.9 IPS |
|
Machine Translation (SP)
|
100% |
228
3.92 IPS |
|
Machine Translation (HP)
|
100% |
225
3.88 IPS |
|
Machine Translation (Q)
|
50% |
152
5.40 IPS |