User | microtechcs |
Upload Date | February 16 2025 05:31 AM |
Views | 8 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm Snapdragon 865+ |
System Information | |
---|---|
Operating System | Android 13 |
Model | Samsung Galaxy Note20 Ultra 5G |
Model ID | samsung SM-N986W |
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 | 10.35 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
175
32.5 IPS |
|
Image Classification (HP)
|
100% |
177
32.9 IPS |
|
Image Classification (Q)
|
100% |
476
88.6 IPS |
|
Image Segmentation (SP)
|
100% |
177
2.87 IPS |
|
Image Segmentation (HP)
|
100% |
187
3.03 IPS |
|
Image Segmentation (Q)
|
98% |
526
8.55 IPS |
|
Pose Estimation (SP)
|
100% |
640
0.75 IPS |
|
Pose Estimation (HP)
|
100% |
631
0.74 IPS |
|
Pose Estimation (Q)
|
84% |
1106
1.31 IPS |
|
Object Detection (SP)
|
100% |
171
13.5 IPS |
|
Object Detection (HP)
|
100% |
167
13.2 IPS |
|
Object Detection (Q)
|
83% |
472
38.1 IPS |
|
Face Detection (SP)
|
100% |
369
4.39 IPS |
|
Face Detection (HP)
|
100% |
371
4.40 IPS |
|
Face Detection (Q)
|
95% |
880
10.5 IPS |
|
Depth Estimation (SP)
|
100% |
514
3.96 IPS |
|
Depth Estimation (HP)
|
99% |
518
3.99 IPS |
|
Depth Estimation (Q)
|
64% |
1046
9.58 IPS |
|
Style Transfer (SP)
|
89% |
1150
1.49 IPS |
|
Style Transfer (HP)
|
89% |
1138
1.48 IPS |
|
Style Transfer (Q)
|
98% |
2509
3.24 IPS |
|
Image Super-Resolution (SP)
|
100% |
308
11.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
284
10.5 IPS |
|
Image Super-Resolution (Q)
|
97% |
632
23.4 IPS |
|
Text Classification (SP)
|
100% |
170
227.5 IPS |
|
Text Classification (HP)
|
100% |
166
222.0 IPS |
|
Text Classification (Q)
|
88% |
268
362.0 IPS |
|
Machine Translation (SP)
|
100% |
248
4.26 IPS |
|
Machine Translation (HP)
|
100% |
245
4.23 IPS |
|
Machine Translation (Q)
|
50% |
155
5.51 IPS |