Upload Date | October 24 2021 12:58 AM |
Views | 2 |
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 | 7.44 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
675
72.3 IPS |
|
Image Classification (F16)
|
100% |
1116
119.6 IPS |
|
Image Classification (I8)
|
80% |
1448
155.1 IPS |
|
Image Segmentation (F32)
|
100% |
864
5.34 IPS |
|
Image Segmentation (F16)
|
100% |
1028
6.35 IPS |
|
Image Segmentation (I8)
|
89% |
2908
18.0 IPS |
|
Pose Estimation (F32)
|
100% |
455
1.84 IPS |
|
Pose Estimation (F16)
|
100% |
1664
6.73 IPS |
|
Pose Estimation (I8)
|
80% |
5232
21.2 IPS |
|
Object Detection (F32)
|
100% |
482
16.9 IPS |
|
Object Detection (F16)
|
100% |
626
22.0 IPS |
|
Object Detection (I8)
|
52% |
1263
44.3 IPS |
|
Face Detection (F32)
|
100% |
881
10.1 IPS |
|
Face Detection (F16)
|
97% |
1085
12.5 IPS |
|
Face Detection (I8)
|
75% |
4152
47.7 IPS |
|
Text Classification (F32)
|
54% |
11
4.23 IPS |
|
Text Classification (F16)
|
54% |
10
4.02 IPS |
|
Machine Translation (F32)
|
100% |
569
87.7 IPS |
|
Machine Translation (F16)
|
100% |
585
90.1 IPS |