Upload Date | February 27 2025 01:36 PM |
Views | 9 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Samsung Exynos 7420 |
System Information | |
---|---|
Operating System | Android 13 |
Model | Samsung Galaxy S6 edge |
Model ID | samsung SM-G925F |
Motherboard | universal7420 |
Governor | interactive |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3335 revision 0 |
Base Frequency | 1.50 GHz |
Cluster 1 | 4 Cores @ 1.50 GHz |
Cluster 2 | 4 Cores @ 2.10 GHz |
Memory Information | |
---|---|
Size | 2.64 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
0% |
0
1.28 KIPS |
|
Image Classification (HP)
|
0% |
0
1.31 KIPS |
|
Image Classification (Q)
|
0% |
0
1.88 KIPS |
|
Image Segmentation (SP)
|
73% |
6941
120.0 IPS |
|
Image Segmentation (HP)
|
73% |
6966
120.4 IPS |
|
Image Segmentation (Q)
|
73% |
16258
281.0 IPS |
|
Pose Estimation (SP)
|
0% |
0
225.1 IPS |
|
Pose Estimation (HP)
|
0% |
0
242.8 IPS |
|
Pose Estimation (Q)
|
0% |
0
1.05 KIPS |
|
Object Detection (SP)
|
0% |
0
480.5 IPS |
|
Object Detection (HP)
|
0% |
0
451.1 IPS |
|
Object Detection (Q)
|
0% |
0
369.9 IPS |
|
Face Detection (SP)
|
0% |
0
165.6 IPS |
|
Face Detection (HP)
|
0% |
0
147.6 IPS |
|
Face Detection (Q)
|
0% |
0
260.7 IPS |
|
Depth Estimation (SP)
|
0% |
0
380.3 IPS |
|
Depth Estimation (HP)
|
0% |
0
416.5 IPS |
|
Depth Estimation (Q)
|
0% |
0
352.6 IPS |
|
Style Transfer (SP)
|
32% |
48360
606.6 IPS |
|
Style Transfer (HP)
|
32% |
50703
636.0 IPS |
|
Style Transfer (Q)
|
0% |
0
2.30 KIPS |
|
Image Super-Resolution (SP)
|
1% |
0
1.19 KIPS |
|
Image Super-Resolution (HP)
|
1% |
0
1.25 KIPS |
|
Image Super-Resolution (Q)
|
2% |
156
1.84 KIPS |
|
Text Classification (SP)
|
29% |
312
5.39 KIPS |
|
Text Classification (HP)
|
29% |
309
5.34 KIPS |
|
Text Classification (Q)
|
29% |
204
3.53 KIPS |
|
Machine Translation (SP)
|
0% |
0
3.19 IPS |
|
Machine Translation (HP)
|
0% |
0
3.03 IPS |
|
Machine Translation (Q)
|
0% |
0
2.53 IPS |