User | GyBHard |
Upload Date | February 06 2025 01:51 PM |
Views | 4 |
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% |
94
17.4 IPS |
|
Image Classification (HP)
|
100% |
164
30.6 IPS |
|
Image Classification (Q)
|
99% |
153
28.5 IPS |
|
Image Segmentation (SP)
|
100% |
130
2.10 IPS |
|
Image Segmentation (HP)
|
100% |
230
3.73 IPS |
|
Image Segmentation (Q)
|
98% |
222
3.62 IPS |
|
Pose Estimation (SP)
|
100% |
93
0.11 IPS |
|
Pose Estimation (HP)
|
100% |
109
0.13 IPS |
|
Pose Estimation (Q)
|
96% |
108
0.13 IPS |
|
Object Detection (SP)
|
100% |
78
6.17 IPS |
|
Object Detection (HP)
|
100% |
130
10.3 IPS |
|
Object Detection (Q)
|
83% |
120
9.69 IPS |
|
Face Detection (SP)
|
100% |
280
3.33 IPS |
|
Face Detection (HP)
|
100% |
413
4.91 IPS |
|
Face Detection (Q)
|
97% |
388
4.63 IPS |
|
Depth Estimation (SP)
|
100% |
175
1.35 IPS |
|
Depth Estimation (HP)
|
99% |
229
1.76 IPS |
|
Depth Estimation (Q)
|
62% |
185
1.75 IPS |
|
Style Transfer (SP)
|
100% |
350
0.45 IPS |
|
Style Transfer (HP)
|
100% |
488
0.63 IPS |
|
Style Transfer (Q)
|
98% |
488
0.63 IPS |
|
Image Super-Resolution (SP)
|
100% |
91
3.35 IPS |
|
Image Super-Resolution (HP)
|
100% |
137
5.05 IPS |
|
Image Super-Resolution (Q)
|
97% |
137
5.07 IPS |
|
Text Classification (SP)
|
100% |
158
211.4 IPS |
|
Text Classification (HP)
|
100% |
157
209.8 IPS |
|
Text Classification (Q)
|
91% |
251
337.8 IPS |
|
Machine Translation (SP)
|
100% |
272
4.68 IPS |
|
Machine Translation (HP)
|
100% |
267
4.60 IPS |
|
Machine Translation (Q)
|
57% |
200
4.90 IPS |