User | M91 |
Upload Date | April 11 2025 12:42 PM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 15 |
Model | samsung SM-A366W |
Model ID | samsung SM-A366W |
Motherboard | parrot |
Governor | walt |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 2 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 4 Cores @ 2.40 GHz |
Memory Information | |
---|---|
Size | 5.16 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
191
35.5 IPS |
|
Image Classification (HP)
|
100% |
453
84.2 IPS |
|
Image Classification (Q)
|
100% |
1448
269.4 IPS |
|
Image Segmentation (SP)
|
100% |
522
8.47 IPS |
|
Image Segmentation (HP)
|
100% |
530
8.59 IPS |
|
Image Segmentation (Q)
|
98% |
1661
27.0 IPS |
|
Pose Estimation (SP)
|
100% |
2019
2.36 IPS |
|
Pose Estimation (HP)
|
100% |
2022
2.36 IPS |
|
Pose Estimation (Q)
|
84% |
3763
4.46 IPS |
|
Object Detection (SP)
|
100% |
455
36.1 IPS |
|
Object Detection (HP)
|
100% |
453
35.9 IPS |
|
Object Detection (Q)
|
83% |
1387
112.1 IPS |
|
Face Detection (SP)
|
100% |
617
7.33 IPS |
|
Face Detection (HP)
|
100% |
1100
13.1 IPS |
|
Face Detection (Q)
|
95% |
3379
40.3 IPS |
|
Depth Estimation (SP)
|
100% |
836
6.44 IPS |
|
Depth Estimation (HP)
|
99% |
815
6.28 IPS |
|
Depth Estimation (Q)
|
64% |
3413
31.3 IPS |
|
Style Transfer (SP)
|
89% |
3624
4.70 IPS |
|
Style Transfer (HP)
|
89% |
3644
4.73 IPS |
|
Style Transfer (Q)
|
98% |
8606
11.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
847
31.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
854
31.5 IPS |
|
Image Super-Resolution (Q)
|
97% |
2031
75.2 IPS |
|
Text Classification (SP)
|
100% |
494
659.8 IPS |
|
Text Classification (HP)
|
100% |
490
654.1 IPS |
|
Text Classification (Q)
|
88% |
918
1.24 KIPS |
|
Machine Translation (SP)
|
100% |
719
12.4 IPS |
|
Machine Translation (HP)
|
100% |
711
12.2 IPS |
|
Machine Translation (Q)
|
50% |
30
1.05 IPS |