Upload Date | November 21 2024 12:16 AM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-A155M |
Model ID | samsung SM-A155M |
Motherboard | a15 |
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 | 7.48 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
212
39.5 IPS |
|
Image Classification (HP)
|
100% |
213
39.6 IPS |
|
Image Classification (Q)
|
100% |
568
105.7 IPS |
|
Image Segmentation (SP)
|
100% |
250
4.05 IPS |
|
Image Segmentation (HP)
|
100% |
252
4.08 IPS |
|
Image Segmentation (Q)
|
98% |
588
9.56 IPS |
|
Pose Estimation (SP)
|
100% |
920
1.07 IPS |
|
Pose Estimation (HP)
|
100% |
854
1.00 IPS |
|
Pose Estimation (Q)
|
84% |
1365
1.62 IPS |
|
Object Detection (SP)
|
100% |
190
15.1 IPS |
|
Object Detection (HP)
|
100% |
184
14.6 IPS |
|
Object Detection (Q)
|
83% |
512
41.4 IPS |
|
Face Detection (SP)
|
100% |
597
7.10 IPS |
|
Face Detection (HP)
|
100% |
609
7.24 IPS |
|
Face Detection (Q)
|
95% |
1196
14.3 IPS |
|
Depth Estimation (SP)
|
100% |
783
6.03 IPS |
|
Depth Estimation (HP)
|
99% |
792
6.10 IPS |
|
Depth Estimation (Q)
|
64% |
1208
11.1 IPS |
|
Style Transfer (SP)
|
89% |
1526
1.98 IPS |
|
Style Transfer (HP)
|
89% |
1502
1.95 IPS |
|
Style Transfer (Q)
|
98% |
3061
3.95 IPS |
|
Image Super-Resolution (SP)
|
100% |
419
15.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
419
15.5 IPS |
|
Image Super-Resolution (Q)
|
97% |
727
26.9 IPS |
|
Text Classification (SP)
|
100% |
211
282.1 IPS |
|
Text Classification (HP)
|
100% |
210
280.5 IPS |
|
Text Classification (Q)
|
88% |
398
536.3 IPS |
|
Machine Translation (SP)
|
100% |
383
6.59 IPS |
|
Machine Translation (HP)
|
100% |
385
6.63 IPS |
|
Machine Translation (Q)
|
50% |
287
10.2 IPS |