User | benched |
Upload Date | October 08 2024 07:19 PM |
Views | 12 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
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% |
177
33.0 IPS |
|
Image Classification (HP)
|
100% |
177
32.9 IPS |
|
Image Classification (Q)
|
100% |
318
59.2 IPS |
|
Image Segmentation (SP)
|
100% |
222
3.60 IPS |
|
Image Segmentation (HP)
|
100% |
222
3.60 IPS |
|
Image Segmentation (Q)
|
98% |
402
6.54 IPS |
|
Pose Estimation (SP)
|
100% |
861
1.01 IPS |
|
Pose Estimation (HP)
|
100% |
862
1.01 IPS |
|
Pose Estimation (Q)
|
84% |
703
0.83 IPS |
|
Object Detection (SP)
|
100% |
172
13.6 IPS |
|
Object Detection (HP)
|
100% |
173
13.7 IPS |
|
Object Detection (Q)
|
83% |
319
25.8 IPS |
|
Face Detection (SP)
|
100% |
499
5.93 IPS |
|
Face Detection (HP)
|
100% |
498
5.92 IPS |
|
Face Detection (Q)
|
95% |
743
8.87 IPS |
|
Depth Estimation (SP)
|
100% |
715
5.51 IPS |
|
Depth Estimation (HP)
|
99% |
703
5.41 IPS |
|
Depth Estimation (Q)
|
64% |
743
6.81 IPS |
|
Style Transfer (SP)
|
89% |
1486
1.93 IPS |
|
Style Transfer (HP)
|
89% |
1487
1.93 IPS |
|
Style Transfer (Q)
|
98% |
1913
2.47 IPS |
|
Image Super-Resolution (SP)
|
100% |
381
14.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
382
14.1 IPS |
|
Image Super-Resolution (Q)
|
97% |
416
15.4 IPS |
|
Text Classification (SP)
|
100% |
203
271.0 IPS |
|
Text Classification (HP)
|
100% |
202
269.0 IPS |
|
Text Classification (Q)
|
88% |
304
410.0 IPS |
|
Machine Translation (SP)
|
100% |
336
5.79 IPS |
|
Machine Translation (HP)
|
100% |
333
5.74 IPS |
|
Machine Translation (Q)
|
50% |
182
6.47 IPS |