Upload Date | May 10 2024 12:26 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 12 |
Model | Xiaomi Mi 10T Pro 5G |
Model ID | Xiaomi M2007J3SG |
Motherboard | apollo |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3341 revision 0 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 3 Cores @ 2.42 GHz |
Cluster 3 | 1 Core @ 2.84 GHz |
Memory Information | |
---|---|
Size | 7.43 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
200
37.5 IPS |
|
Image Classification (F16)
|
100% |
198
37.0 IPS |
|
Image Classification (I8)
|
97% |
463
86.6 IPS |
|
Image Segmentation (F32)
|
100% |
328
5.48 IPS |
|
Image Segmentation (F16)
|
100% |
328
5.48 IPS |
|
Image Segmentation (I8)
|
98% |
412
6.88 IPS |
|
Pose Estimation (F32)
|
100% |
540
0.65 IPS |
|
Pose Estimation (F16)
|
100% |
531
0.64 IPS |
|
Pose Estimation (I8)
|
100% |
2403
2.91 IPS |
|
Object Detection (F32)
|
100% |
246
18.4 IPS |
|
Object Detection (F16)
|
100% |
245
18.3 IPS |
|
Object Detection (I8)
|
61% |
645
48.2 IPS |
|
Face Detection (F32)
|
100% |
527
6.27 IPS |
|
Face Detection (F16)
|
100% |
533
6.34 IPS |
|
Face Detection (I8)
|
86% |
1228
14.6 IPS |
|
Depth Estimation (F32)
|
100% |
465
3.61 IPS |
|
Depth Estimation (F16)
|
100% |
487
3.78 IPS |
|
Depth Estimation (I8)
|
95% |
1130
8.77 IPS |
|
Style Transfer (F32)
|
100% |
859
1.13 IPS |
|
Style Transfer (F16)
|
100% |
854
1.12 IPS |
|
Style Transfer (I8)
|
98% |
1921
2.53 IPS |
|
Image Super-Resolution (F32)
|
100% |
278
9.92 IPS |
|
Image Super-Resolution (F16)
|
100% |
267
9.53 IPS |
|
Image Super-Resolution (I8)
|
98% |
1141
40.7 IPS |
|
Text Classification (F32)
|
100% |
244
350.3 IPS |
|
Text Classification (F16)
|
100% |
257
369.2 IPS |
|
Text Classification (I8)
|
92% |
257
369.4 IPS |
|
Machine Translation (F32)
|
100% |
455
8.38 IPS |
|
Machine Translation (F16)
|
100% |
456
8.39 IPS |
|
Machine Translation (I8)
|
64% |
227
4.17 IPS |