Upload Date | January 12 2025 01:53 PM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm Snapdragon 865 |
System Information | |
---|---|
Operating System | Android 13 |
Model | Samsung Galaxy Z Fold2 5G |
Model ID | samsung SM-F916B |
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% |
511
95.0 IPS |
|
Image Classification (HP)
|
100% |
518
96.4 IPS |
|
Image Classification (Q)
|
100% |
1494
277.8 IPS |
|
Image Segmentation (SP)
|
100% |
649
10.5 IPS |
|
Image Segmentation (HP)
|
100% |
614
9.95 IPS |
|
Image Segmentation (Q)
|
98% |
1696
27.6 IPS |
|
Pose Estimation (SP)
|
100% |
2208
2.58 IPS |
|
Pose Estimation (HP)
|
100% |
2071
2.42 IPS |
|
Pose Estimation (Q)
|
84% |
3319
3.94 IPS |
|
Object Detection (SP)
|
100% |
458
36.3 IPS |
|
Object Detection (HP)
|
100% |
458
36.3 IPS |
|
Object Detection (Q)
|
83% |
1283
103.6 IPS |
|
Face Detection (SP)
|
100% |
1475
17.5 IPS |
|
Face Detection (HP)
|
100% |
1467
17.4 IPS |
|
Face Detection (Q)
|
95% |
3127
37.3 IPS |
|
Depth Estimation (SP)
|
100% |
1745
13.4 IPS |
|
Depth Estimation (HP)
|
99% |
1721
13.3 IPS |
|
Depth Estimation (Q)
|
64% |
3121
28.6 IPS |
|
Style Transfer (SP)
|
89% |
3671
4.77 IPS |
|
Style Transfer (HP)
|
89% |
3651
4.74 IPS |
|
Style Transfer (Q)
|
98% |
7540
9.72 IPS |
|
Image Super-Resolution (SP)
|
100% |
1030
38.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
293
10.8 IPS |
|
Image Super-Resolution (Q)
|
97% |
634
23.5 IPS |
|
Text Classification (SP)
|
100% |
171
227.6 IPS |
|
Text Classification (HP)
|
100% |
162
215.6 IPS |
|
Text Classification (Q)
|
88% |
244
329.7 IPS |
|
Machine Translation (SP)
|
100% |
255
4.40 IPS |
|
Machine Translation (HP)
|
100% |
253
4.35 IPS |
|
Machine Translation (Q)
|
50% |
145
5.13 IPS |