Upload Date | June 13 2021 02:00 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 11 |
Model | Samsung Galaxy Tab S7+ |
Model ID | samsung SM-T970 |
Motherboard | kona |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3341 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 @ 3.09 GHz |
Memory Information | |
---|---|
Size | 7.38 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
669
71.6 IPS |
|
Image Classification (F16)
|
100% |
1118
119.8 IPS |
|
Image Classification (I8)
|
80% |
1283
137.5 IPS |
|
Image Segmentation (F32)
|
100% |
831
5.13 IPS |
|
Image Segmentation (F16)
|
100% |
1053
6.50 IPS |
|
Image Segmentation (I8)
|
89% |
2720
16.8 IPS |
|
Pose Estimation (F32)
|
100% |
455
1.84 IPS |
|
Pose Estimation (F16)
|
100% |
1671
6.76 IPS |
|
Pose Estimation (I8)
|
80% |
5203
21.1 IPS |
|
Object Detection (F32)
|
100% |
495
17.4 IPS |
|
Object Detection (F16)
|
100% |
645
22.6 IPS |
|
Object Detection (I8)
|
52% |
1198
42.0 IPS |
|
Face Detection (F32)
|
100% |
940
10.8 IPS |
|
Face Detection (F16)
|
97% |
1067
12.3 IPS |
|
Face Detection (I8)
|
75% |
3957
45.5 IPS |
|
Text Classification (F32)
|
54% |
10
4.13 IPS |
|
Text Classification (F16)
|
54% |
10
4.01 IPS |
|
Machine Translation (F32)
|
100% |
570
87.8 IPS |
|
Machine Translation (F16)
|
100% |
583
89.8 IPS |