User | harsidh |
Upload Date | July 06 2025 08:54 AM |
Views | 6 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Samsung Exynos 9611 |
System Information | |
---|---|
Operating System | Android 12 |
Model | Samsung Galaxy M31 |
Model ID | samsung SM-M315F |
Motherboard | exynos9611 |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 0 part 3337 revision 2 |
Base Frequency | 1.74 GHz |
Cluster 1 | 4 Cores @ 1.74 GHz |
Cluster 2 | 4 Cores @ 2.31 GHz |
Memory Information | |
---|---|
Size | 5.44 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
140
26.0 IPS |
|
Image Classification (HP)
|
100% |
139
25.8 IPS |
|
Image Classification (Q)
|
100% |
245
45.5 IPS |
|
Image Segmentation (SP)
|
100% |
178
2.88 IPS |
|
Image Segmentation (HP)
|
100% |
180
2.91 IPS |
|
Image Segmentation (Q)
|
98% |
321
5.22 IPS |
|
Pose Estimation (SP)
|
100% |
679
0.79 IPS |
|
Pose Estimation (HP)
|
100% |
667
0.78 IPS |
|
Pose Estimation (Q)
|
84% |
518
0.61 IPS |
|
Object Detection (SP)
|
100% |
126
10.0 IPS |
|
Object Detection (HP)
|
100% |
125
9.90 IPS |
|
Object Detection (Q)
|
83% |
233
18.8 IPS |
|
Face Detection (SP)
|
100% |
407
4.84 IPS |
|
Face Detection (HP)
|
100% |
405
4.81 IPS |
|
Face Detection (Q)
|
95% |
569
6.79 IPS |
|
Depth Estimation (SP)
|
100% |
530
4.09 IPS |
|
Depth Estimation (HP)
|
99% |
525
4.04 IPS |
|
Depth Estimation (Q)
|
64% |
524
4.80 IPS |
|
Style Transfer (SP)
|
89% |
1111
1.44 IPS |
|
Style Transfer (HP)
|
89% |
1115
1.45 IPS |
|
Style Transfer (Q)
|
98% |
1362
1.76 IPS |
|
Image Super-Resolution (SP)
|
100% |
295
10.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
295
10.9 IPS |
|
Image Super-Resolution (Q)
|
97% |
304
11.3 IPS |
|
Text Classification (SP)
|
100% |
147
196.0 IPS |
|
Text Classification (HP)
|
100% |
144
192.6 IPS |
|
Text Classification (Q)
|
88% |
214
288.9 IPS |
|
Machine Translation (SP)
|
100% |
239
4.11 IPS |
|
Machine Translation (HP)
|
100% |
236
4.07 IPS |
|
Machine Translation (Q)
|
50% |
135
4.78 IPS |