Upload Date | May 08 2025 01:20 AM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm Snapdragon 888 |
System Information | |
---|---|
Operating System | Android 15 |
Model | Samsung Galaxy Z Fold3 5G |
Model ID | samsung SM-F926N |
Motherboard | lahaina |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM SM8350 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3396 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 | 11.09 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
423
78.7 IPS |
|
Image Classification (HP)
|
100% |
457
85.1 IPS |
|
Image Classification (Q)
|
100% |
1318
245.1 IPS |
|
Image Segmentation (SP)
|
100% |
549
8.90 IPS |
|
Image Segmentation (HP)
|
100% |
535
8.68 IPS |
|
Image Segmentation (Q)
|
98% |
1519
24.7 IPS |
|
Pose Estimation (SP)
|
100% |
1822
2.13 IPS |
|
Pose Estimation (HP)
|
100% |
1781
2.08 IPS |
|
Pose Estimation (Q)
|
84% |
2281
2.71 IPS |
|
Object Detection (SP)
|
100% |
325
25.8 IPS |
|
Object Detection (HP)
|
100% |
342
27.1 IPS |
|
Object Detection (Q)
|
83% |
895
72.3 IPS |
|
Face Detection (SP)
|
100% |
1167
13.9 IPS |
|
Face Detection (HP)
|
100% |
1169
13.9 IPS |
|
Face Detection (Q)
|
95% |
2249
26.9 IPS |
|
Depth Estimation (SP)
|
100% |
1565
12.1 IPS |
|
Depth Estimation (HP)
|
99% |
1564
12.1 IPS |
|
Depth Estimation (Q)
|
64% |
2157
19.8 IPS |
|
Style Transfer (SP)
|
89% |
2793
3.63 IPS |
|
Style Transfer (HP)
|
89% |
2777
3.60 IPS |
|
Style Transfer (Q)
|
98% |
5224
6.74 IPS |
|
Image Super-Resolution (SP)
|
100% |
830
30.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
848
31.3 IPS |
|
Image Super-Resolution (Q)
|
97% |
636
23.6 IPS |
|
Text Classification (SP)
|
100% |
163
218.1 IPS |
|
Text Classification (HP)
|
100% |
162
216.5 IPS |
|
Text Classification (Q)
|
88% |
267
359.8 IPS |
|
Machine Translation (SP)
|
100% |
248
4.27 IPS |
|
Machine Translation (HP)
|
100% |
241
4.14 IPS |
|
Machine Translation (Q)
|
50% |
149
5.30 IPS |