Upload Date | January 16 2025 01:57 AM |
Views | 4 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Samsung Exynos 990 |
System Information | |
---|---|
Operating System | Android 13 |
Model | Samsung Galaxy Note20 5G |
Model ID | samsung SM-N981B |
Motherboard | exynos990 |
Governor | energy_step |
CPU Information | |
---|---|
Name | ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 83 architecture 8 variant 1 part 4 revision 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 4 Cores @ 2.00 GHz |
Cluster 2 | 2 Cores @ 2.50 GHz |
Cluster 3 | 2 Cores @ 2.73 GHz |
Memory Information | |
---|---|
Size | 7.27 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
166
30.9 IPS |
|
Image Classification (HP)
|
100% |
275
51.2 IPS |
|
Image Classification (Q)
|
99% |
261
48.8 IPS |
|
Image Segmentation (SP)
|
100% |
235
3.81 IPS |
|
Image Segmentation (HP)
|
100% |
375
6.08 IPS |
|
Image Segmentation (Q)
|
98% |
361
5.87 IPS |
|
Pose Estimation (SP)
|
100% |
127
0.15 IPS |
|
Pose Estimation (HP)
|
100% |
159
0.19 IPS |
|
Pose Estimation (Q)
|
96% |
158
0.18 IPS |
|
Object Detection (SP)
|
100% |
138
11.0 IPS |
|
Object Detection (HP)
|
100% |
222
17.6 IPS |
|
Object Detection (Q)
|
83% |
208
16.8 IPS |
|
Face Detection (SP)
|
100% |
574
6.82 IPS |
|
Face Detection (HP)
|
100% |
838
9.96 IPS |
|
Face Detection (Q)
|
97% |
784
9.35 IPS |
|
Depth Estimation (SP)
|
100% |
248
1.91 IPS |
|
Depth Estimation (HP)
|
99% |
332
2.56 IPS |
|
Depth Estimation (Q)
|
62% |
269
2.54 IPS |
|
Style Transfer (SP)
|
100% |
557
0.72 IPS |
|
Style Transfer (HP)
|
100% |
915
1.18 IPS |
|
Style Transfer (Q)
|
98% |
912
1.18 IPS |
|
Image Super-Resolution (SP)
|
100% |
156
5.76 IPS |
|
Image Super-Resolution (HP)
|
100% |
245
9.03 IPS |
|
Image Super-Resolution (Q)
|
97% |
242
8.97 IPS |
|
Text Classification (SP)
|
100% |
117
155.7 IPS |
|
Text Classification (HP)
|
100% |
128
171.4 IPS |
|
Text Classification (Q)
|
91% |
238
320.2 IPS |
|
Machine Translation (SP)
|
100% |
186
3.21 IPS |
|
Machine Translation (HP)
|
100% |
181
3.12 IPS |
|
Machine Translation (Q)
|
57% |
174
4.26 IPS |