Upload Date | April 26 2024 06:36 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi 2311DRK48C |
Model ID | Xiaomi 2311DRK48C |
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 | 11.08 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
312
58.4 IPS |
|
Image Classification (F16)
|
100% |
420
78.6 IPS |
|
Image Classification (I8)
|
97% |
358
67.1 IPS |
|
Image Segmentation (F32)
|
100% |
695
11.6 IPS |
|
Image Segmentation (F16)
|
100% |
780
13.0 IPS |
|
Image Segmentation (I8)
|
98% |
769
12.8 IPS |
|
Pose Estimation (F32)
|
100% |
353
0.43 IPS |
|
Pose Estimation (F16)
|
100% |
493
0.60 IPS |
|
Pose Estimation (I8)
|
100% |
492
0.60 IPS |
|
Object Detection (F32)
|
100% |
265
19.8 IPS |
|
Object Detection (F16)
|
100% |
334
24.9 IPS |
|
Object Detection (I8)
|
62% |
370
27.6 IPS |
|
Face Detection (F32)
|
100% |
1254
14.9 IPS |
|
Face Detection (F16)
|
98% |
1401
16.7 IPS |
|
Face Detection (I8)
|
86% |
1295
15.4 IPS |
|
Depth Estimation (F32)
|
100% |
704
5.46 IPS |
|
Depth Estimation (F16)
|
100% |
857
6.64 IPS |
|
Depth Estimation (I8)
|
95% |
848
6.58 IPS |
|
Style Transfer (F32)
|
100% |
1922
2.53 IPS |
|
Style Transfer (F16)
|
100% |
2374
3.12 IPS |
|
Style Transfer (I8)
|
98% |
2377
3.13 IPS |
|
Image Super-Resolution (F32)
|
100% |
412
14.7 IPS |
|
Image Super-Resolution (F16)
|
100% |
498
17.8 IPS |
|
Image Super-Resolution (I8)
|
98% |
494
17.6 IPS |
|
Text Classification (F32)
|
100% |
194
278.9 IPS |
|
Text Classification (F16)
|
100% |
194
278.4 IPS |
|
Text Classification (I8)
|
92% |
339
487.4 IPS |
|
Machine Translation (F32)
|
100% |
357
6.58 IPS |
|
Machine Translation (F16)
|
100% |
359
6.60 IPS |
|
Machine Translation (I8)
|
64% |
400
7.36 IPS |