User | benched |
Upload Date | October 08 2024 08:11 PM |
Views | 13 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM Qualcomm |
System Information | |
---|---|
Operating System | Android 13 |
Model | Xiaomi 220333QNY |
Model ID | Xiaomi 220333QNY |
Motherboard | rain |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM Qualcomm |
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 | 3.56 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
32
5.95 IPS |
|
Image Classification (HP)
|
100% |
65
12.1 IPS |
|
Image Classification (Q)
|
97% |
67
12.4 IPS |
|
Image Segmentation (SP)
|
100% |
31
0.51 IPS |
|
Image Segmentation (HP)
|
100% |
106
1.72 IPS |
|
Image Segmentation (Q)
|
98% |
107
1.74 IPS |
|
Pose Estimation (SP)
|
100% |
56
0.07 IPS |
|
Pose Estimation (HP)
|
100% |
111
0.13 IPS |
|
Pose Estimation (Q)
|
95% |
111
0.13 IPS |
|
Object Detection (SP)
|
100% |
32
2.55 IPS |
|
Object Detection (HP)
|
100% |
54
4.30 IPS |
|
Object Detection (Q)
|
89% |
54
4.29 IPS |
|
Face Detection (SP)
|
100% |
80
0.95 IPS |
|
Face Detection (HP)
|
100% |
199
2.37 IPS |
|
Face Detection (Q)
|
97% |
205
2.45 IPS |
|
Depth Estimation (SP)
|
100% |
75
0.58 IPS |
|
Depth Estimation (HP)
|
99% |
155
1.20 IPS |
|
Depth Estimation (Q)
|
62% |
126
1.20 IPS |
|
Style Transfer (SP)
|
0
|
||
Style Transfer (HP)
|
100% |
295
0.38 IPS |
|
Style Transfer (Q)
|
98% |
293
0.38 IPS |
|
Image Super-Resolution (SP)
|
100% |
37
1.38 IPS |
|
Image Super-Resolution (HP)
|
100% |
79
2.91 IPS |
|
Image Super-Resolution (Q)
|
97% |
78
2.90 IPS |
|
Text Classification (SP)
|
100% |
71
95.2 IPS |
|
Text Classification (HP)
|
100% |
72
95.7 IPS |
|
Text Classification (Q)
|
91% |
92
123.3 IPS |
|
Machine Translation (SP)
|
100% |
126
2.17 IPS |
|
Machine Translation (HP)
|
100% |
125
2.16 IPS |
|
Machine Translation (Q)
|
57% |
93
2.26 IPS |