Upload Date | January 10 2025 09:21 AM |
Views | 3 |
System Information | |
---|---|
Operating System | Android 15 |
Model | vivo V2408A |
Model ID | vivo V2408A |
Motherboard | sun |
Governor | walt |
CPU Information | |
---|---|
Name | Qualcomm ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 3 part 1 revision 4 |
Base Frequency | 3.53 GHz |
Cluster 1 | 6 Cores @ 3.53 GHz |
Cluster 2 | 2 Cores @ 4.32 GHz |
Memory Information | |
---|---|
Size | 14.76 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
262
49.1 IPS |
|
Image Classification (F16)
|
100% |
262
49.1 IPS |
|
Image Classification (I8)
|
97% |
670
125.3 IPS |
|
Image Segmentation (F32)
|
100% |
338
5.64 IPS |
|
Image Segmentation (F16)
|
100% |
338
5.65 IPS |
|
Image Segmentation (I8)
|
98% |
650
10.9 IPS |
|
Pose Estimation (F32)
|
100% |
468
0.57 IPS |
|
Pose Estimation (F16)
|
100% |
471
0.57 IPS |
|
Pose Estimation (I8)
|
100% |
1781
2.16 IPS |
|
Object Detection (F32)
|
100% |
269
20.1 IPS |
|
Object Detection (F16)
|
100% |
267
20.0 IPS |
|
Object Detection (I8)
|
61% |
738
55.1 IPS |
|
Face Detection (F32)
|
100% |
695
8.26 IPS |
|
Face Detection (F16)
|
100% |
693
8.23 IPS |
|
Face Detection (I8)
|
86% |
1573
18.7 IPS |
|
Depth Estimation (F32)
|
100% |
609
4.72 IPS |
|
Depth Estimation (F16)
|
100% |
608
4.72 IPS |
|
Depth Estimation (I8)
|
95% |
1649
12.8 IPS |
|
Style Transfer (F32)
|
100% |
1080
1.42 IPS |
|
Style Transfer (F16)
|
100% |
1079
1.42 IPS |
|
Style Transfer (I8)
|
98% |
2834
3.73 IPS |
|
Image Super-Resolution (F32)
|
100% |
322
11.5 IPS |
|
Image Super-Resolution (F16)
|
100% |
322
11.5 IPS |
|
Image Super-Resolution (I8)
|
98% |
1149
41.1 IPS |
|
Text Classification (F32)
|
100% |
370
531.1 IPS |
|
Text Classification (F16)
|
100% |
369
530.3 IPS |
|
Text Classification (I8)
|
92% |
577
829.0 IPS |
|
Machine Translation (F32)
|
100% |
671
12.3 IPS |
|
Machine Translation (F16)
|
100% |
668
12.3 IPS |
|
Machine Translation (I8)
|
64% |
682
12.5 IPS |