User | Kosst_Amojan |
Upload Date | April 22 2022 12:53 PM |
Views | 4 |
System Information | |
---|---|
Operating System | Android 12 |
Model | samsung SM-S908B |
Model ID | samsung SM-S908B |
Motherboard | s5e9925 |
Governor | energy_aware |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 2 part 3400 revision 0 |
Base Frequency | 1.82 GHz |
Cluster 1 | 4 Cores @ 1.82 GHz |
Cluster 2 | 3 Cores @ 2.52 GHz |
Cluster 3 | 1 Core @ 2.80 GHz |
Memory Information | |
---|---|
Size | 10.27 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
420
45.0 IPS |
|
Image Classification (F16)
|
100% |
413
44.2 IPS |
|
Image Classification (I8)
|
81% |
194
20.8 IPS |
|
Image Segmentation (F32)
|
100% |
708
4.37 IPS |
|
Image Segmentation (F16)
|
100% |
691
4.27 IPS |
|
Image Segmentation (I8)
|
89% |
910
5.62 IPS |
|
Pose Estimation (F32)
|
100% |
320
1.29 IPS |
|
Pose Estimation (F16)
|
100% |
308
1.25 IPS |
|
Pose Estimation (I8)
|
80% |
263
1.06 IPS |
|
Object Detection (F32)
|
100% |
487
17.1 IPS |
|
Object Detection (F16)
|
100% |
492
17.3 IPS |
|
Object Detection (I8)
|
52% |
300
10.5 IPS |
|
Face Detection (F32)
|
100% |
691
7.94 IPS |
|
Face Detection (F16)
|
100% |
711
8.17 IPS |
|
Face Detection (I8)
|
75% |
509
5.84 IPS |
|
Text Classification (F32)
|
100% |
322
127.5 IPS |
|
Text Classification (F16)
|
100% |
325
128.5 IPS |
|
Machine Translation (F32)
|
100% |
788
121.5 IPS |
|
Machine Translation (F16)
|
100% |
785
121.0 IPS |