User | GyBHard |
Upload Date | August 26 2025 09:16 AM |
Views | 6 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-A245M |
Model ID | samsung SM-A245M |
Motherboard | a24 |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 4 part 3339 revision 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 6 Cores @ 2.00 GHz |
Cluster 2 | 2 Cores @ 2.20 GHz |
Memory Information | |
---|---|
Size | 5.53 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
177
32.8 IPS |
|
Image Classification (HP)
|
100% |
199
37.0 IPS |
|
Image Classification (Q)
|
97% |
184
34.3 IPS |
|
Image Segmentation (SP)
|
100% |
260
4.22 IPS |
|
Image Segmentation (HP)
|
100% |
540
8.75 IPS |
|
Image Segmentation (Q)
|
98% |
503
8.17 IPS |
|
Pose Estimation (SP)
|
100% |
1151
1.34 IPS |
|
Pose Estimation (HP)
|
100% |
2003
2.34 IPS |
|
Pose Estimation (Q)
|
95% |
1990
2.33 IPS |
|
Object Detection (SP)
|
100% |
147
11.6 IPS |
|
Object Detection (HP)
|
99% |
288
22.9 IPS |
|
Object Detection (Q)
|
83% |
284
23.0 IPS |
|
Face Detection (SP)
|
100% |
590
7.01 IPS |
|
Face Detection (HP)
|
100% |
1098
13.0 IPS |
|
Face Detection (Q)
|
96% |
1067
12.7 IPS |
|
Depth Estimation (SP)
|
100% |
757
5.83 IPS |
|
Depth Estimation (HP)
|
98% |
1480
11.4 IPS |
|
Depth Estimation (Q)
|
62% |
1185
11.3 IPS |
|
Style Transfer (SP)
|
100% |
1939
2.49 IPS |
|
Style Transfer (HP)
|
100% |
4006
5.15 IPS |
|
Style Transfer (Q)
|
98% |
3916
5.05 IPS |
|
Image Super-Resolution (SP)
|
100% |
457
16.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
743
27.4 IPS |
|
Image Super-Resolution (Q)
|
97% |
634
23.5 IPS |
|
Text Classification (SP)
|
35% |
6
50.2 IPS |
|
Text Classification (HP)
|
35% |
8
78.8 IPS |
|
Text Classification (Q)
|
32% |
6
77.2 IPS |
|
Machine Translation (SP)
|
100% |
146
2.52 IPS |
|
Machine Translation (HP)
|
100% |
174
2.99 IPS |
|
Machine Translation (Q)
|
43% |
42
2.47 IPS |