Upload Date | December 09 2022 05:56 AM |
Views | 3 |
System Information | |
---|---|
Operating System | Android 11 |
Model | samsung SM-T875N |
Model ID | samsung SM-T875N |
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 | 5.45 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
705
75.6 IPS |
|
Image Classification (F16)
|
100% |
1135
121.6 IPS |
|
Image Classification (I8)
|
80% |
1292
138.4 IPS |
|
Image Segmentation (F32)
|
100% |
886
5.47 IPS |
|
Image Segmentation (F16)
|
100% |
1125
6.95 IPS |
|
Image Segmentation (I8)
|
89% |
2820
17.4 IPS |
|
Pose Estimation (F32)
|
100% |
463
1.87 IPS |
|
Pose Estimation (F16)
|
100% |
1685
6.82 IPS |
|
Pose Estimation (I8)
|
80% |
5275
21.3 IPS |
|
Object Detection (F32)
|
100% |
544
19.1 IPS |
|
Object Detection (F16)
|
100% |
613
21.5 IPS |
|
Object Detection (I8)
|
52% |
1226
43.0 IPS |
|
Face Detection (F32)
|
100% |
972
11.2 IPS |
|
Face Detection (F16)
|
97% |
1126
12.9 IPS |
|
Face Detection (I8)
|
75% |
4229
48.6 IPS |
|
Text Classification (F32)
|
54% |
11
4.33 IPS |
|
Text Classification (F16)
|
54% |
11
4.22 IPS |
|
Machine Translation (F32)
|
100% |
593
91.3 IPS |
|
Machine Translation (F16)
|
100% |
573
88.4 IPS |