Upload Date | March 27 2024 07:14 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi 2311DRK48G |
Model ID | Xiaomi 2311DRK48G |
Motherboard | duchamp |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3405 revision 0 |
Base Frequency | 2.20 GHz |
Cluster 1 | 4 Cores @ 2.20 GHz |
Cluster 2 | 3 Cores @ 3.20 GHz |
Cluster 3 | 1 Core @ 3.35 GHz |
Memory Information | |
---|---|
Size | 7.17 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
322
60.2 IPS |
|
Image Classification (F16)
|
100% |
431
80.7 IPS |
|
Image Classification (I8)
|
97% |
377
70.5 IPS |
|
Image Segmentation (F32)
|
100% |
710
11.9 IPS |
|
Image Segmentation (F16)
|
100% |
812
13.6 IPS |
|
Image Segmentation (I8)
|
98% |
796
13.3 IPS |
|
Pose Estimation (F32)
|
100% |
357
0.43 IPS |
|
Pose Estimation (F16)
|
100% |
499
0.60 IPS |
|
Pose Estimation (I8)
|
100% |
496
0.60 IPS |
|
Object Detection (F32)
|
100% |
275
20.6 IPS |
|
Object Detection (F16)
|
100% |
344
25.7 IPS |
|
Object Detection (I8)
|
62% |
347
25.9 IPS |
|
Face Detection (F32)
|
100% |
1357
16.1 IPS |
|
Face Detection (F16)
|
98% |
1433
17.0 IPS |
|
Face Detection (I8)
|
86% |
1375
16.3 IPS |
|
Depth Estimation (F32)
|
100% |
720
5.59 IPS |
|
Depth Estimation (F16)
|
100% |
863
6.69 IPS |
|
Depth Estimation (I8)
|
95% |
861
6.68 IPS |
|
Style Transfer (F32)
|
100% |
1942
2.55 IPS |
|
Style Transfer (F16)
|
100% |
2376
3.13 IPS |
|
Style Transfer (I8)
|
98% |
2378
3.13 IPS |
|
Image Super-Resolution (F32)
|
100% |
431
15.4 IPS |
|
Image Super-Resolution (F16)
|
100% |
503
18.0 IPS |
|
Image Super-Resolution (I8)
|
98% |
498
17.8 IPS |
|
Text Classification (F32)
|
100% |
234
337.0 IPS |
|
Text Classification (F16)
|
100% |
233
335.0 IPS |
|
Text Classification (I8)
|
92% |
402
577.2 IPS |
|
Machine Translation (F32)
|
100% |
426
7.84 IPS |
|
Machine Translation (F16)
|
100% |
428
7.88 IPS |
|
Machine Translation (I8)
|
64% |
456
8.40 IPS |