Upload Date | October 21 2024 04:44 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi 2201122C |
Model ID | Xiaomi 2201122C |
Motherboard | taro |
Governor | walt |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 2 part 3400 revision 0 |
Base Frequency | 1.78 GHz |
Cluster 1 | 4 Cores @ 1.79 GHz |
Cluster 2 | 3 Cores @ 2.50 GHz |
Cluster 3 | 1 Core @ 3.00 GHz |
Memory Information | |
---|---|
Size | 10.93 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
351
65.7 IPS |
|
Image Classification (F16)
|
100% |
510
95.4 IPS |
|
Image Classification (I8)
|
97% |
476
89.2 IPS |
|
Image Segmentation (F32)
|
100% |
638
10.6 IPS |
|
Image Segmentation (F16)
|
100% |
943
15.8 IPS |
|
Image Segmentation (I8)
|
98% |
884
14.8 IPS |
|
Pose Estimation (F32)
|
100% |
561
0.68 IPS |
|
Pose Estimation (F16)
|
100% |
1041
1.26 IPS |
|
Pose Estimation (I8)
|
100% |
983
1.19 IPS |
|
Object Detection (F32)
|
100% |
257
19.2 IPS |
|
Object Detection (F16)
|
100% |
409
30.5 IPS |
|
Object Detection (I8)
|
62% |
364
27.2 IPS |
|
Face Detection (F32)
|
100% |
1198
14.2 IPS |
|
Face Detection (F16)
|
97% |
1796
21.4 IPS |
|
Face Detection (I8)
|
87% |
1628
19.4 IPS |
|
Depth Estimation (F32)
|
100% |
851
6.60 IPS |
|
Depth Estimation (F16)
|
100% |
1544
12.0 IPS |
|
Depth Estimation (I8)
|
95% |
1516
11.8 IPS |
|
Style Transfer (F32)
|
100% |
1866
2.45 IPS |
|
Style Transfer (F16)
|
100% |
3792
4.99 IPS |
|
Style Transfer (I8)
|
98% |
3762
4.95 IPS |
|
Image Super-Resolution (F32)
|
100% |
295
10.5 IPS |
|
Image Super-Resolution (F16)
|
100% |
378
13.5 IPS |
|
Image Super-Resolution (I8)
|
98% |
449
16.0 IPS |
|
Text Classification (F32)
|
100% |
166
239.1 IPS |
|
Text Classification (F16)
|
100% |
166
238.1 IPS |
|
Text Classification (I8)
|
92% |
296
426.1 IPS |
|
Machine Translation (F32)
|
100% |
300
5.52 IPS |
|
Machine Translation (F16)
|
100% |
303
5.57 IPS |
|
Machine Translation (I8)
|
64% |
355
6.53 IPS |