Upload Date | August 27 2024 10:08 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 13 |
Model | samsung SM-G7810 |
Model ID | samsung SM-G7810 |
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 @ 2.84 GHz |
Memory Information | |
---|---|
Size | 7.44 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
635
68.0 IPS |
|
Image Classification (F16)
|
100% |
1013
108.5 IPS |
|
Image Classification (I8)
|
80% |
1309
140.3 IPS |
|
Image Segmentation (F32)
|
100% |
991
6.12 IPS |
|
Image Segmentation (F16)
|
100% |
1200
7.41 IPS |
|
Image Segmentation (I8)
|
89% |
3396
21.0 IPS |
|
Pose Estimation (F32)
|
100% |
406
1.64 IPS |
|
Pose Estimation (F16)
|
100% |
1512
6.12 IPS |
|
Pose Estimation (I8)
|
80% |
5457
22.1 IPS |
|
Object Detection (F32)
|
100% |
777
27.3 IPS |
|
Object Detection (F16)
|
100% |
1250
43.9 IPS |
|
Object Detection (I8)
|
52% |
2296
80.6 IPS |
|
Face Detection (F32)
|
100% |
973
11.2 IPS |
|
Face Detection (F16)
|
97% |
1202
13.8 IPS |
|
Face Detection (I8)
|
75% |
4092
47.0 IPS |
|
Text Classification (F32)
|
54% |
12
4.71 IPS |
|
Text Classification (F16)
|
54% |
12
4.78 IPS |
|
Machine Translation (F32)
|
100% |
557
85.8 IPS |
|
Machine Translation (F16)
|
100% |
550
84.7 IPS |