Upload Date | August 30 2024 10:45 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Xiaomi 2106118C |
Model ID | Xiaomi 2106118C |
Motherboard | odin |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM Odin |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3396 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 @ 3.00 GHz |
Memory Information | |
---|---|
Size | 7.05 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
305
57.2 IPS |
|
Image Classification (F16)
|
100% |
276
51.6 IPS |
|
Image Classification (I8)
|
97% |
263
49.2 IPS |
|
Image Segmentation (F32)
|
100% |
464
7.74 IPS |
|
Image Segmentation (F16)
|
100% |
574
9.59 IPS |
|
Image Segmentation (I8)
|
98% |
564
9.42 IPS |
|
Pose Estimation (F32)
|
100% |
514
0.62 IPS |
|
Pose Estimation (F16)
|
100% |
318
0.39 IPS |
|
Pose Estimation (I8)
|
100% |
306
0.37 IPS |
|
Object Detection (F32)
|
100% |
193
14.4 IPS |
|
Object Detection (F16)
|
100% |
195
14.6 IPS |
|
Object Detection (I8)
|
62% |
197
14.7 IPS |
|
Face Detection (F32)
|
100% |
969
11.5 IPS |
|
Face Detection (F16)
|
97% |
1278
15.2 IPS |
|
Face Detection (I8)
|
87% |
1189
14.1 IPS |
|
Depth Estimation (F32)
|
100% |
731
5.67 IPS |
|
Depth Estimation (F16)
|
100% |
869
6.74 IPS |
|
Depth Estimation (I8)
|
95% |
878
6.81 IPS |
|
Style Transfer (F32)
|
100% |
1500
1.97 IPS |
|
Style Transfer (F16)
|
100% |
2577
3.39 IPS |
|
Style Transfer (I8)
|
98% |
2424
3.19 IPS |
|
Image Super-Resolution (F32)
|
100% |
373
13.3 IPS |
|
Image Super-Resolution (F16)
|
100% |
568
20.3 IPS |
|
Image Super-Resolution (I8)
|
98% |
560
20.0 IPS |
|
Text Classification (F32)
|
100% |
243
349.3 IPS |
|
Text Classification (F16)
|
100% |
242
347.6 IPS |
|
Text Classification (I8)
|
92% |
391
561.7 IPS |
|
Machine Translation (F32)
|
100% |
404
7.43 IPS |
|
Machine Translation (F16)
|
100% |
405
7.45 IPS |
|
Machine Translation (I8)
|
64% |
440
8.10 IPS |