User | inc7007 |
Upload Date | January 18 2025 09:31 PM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM MT6877V/TTZA |
System Information | |
---|---|
Operating System | Android 14 |
Model | samsung SM-A346B |
Model ID | samsung SM-A346B |
Motherboard | a34x |
CPU Information | |
---|---|
Name | ARM MT6877V/TTZA |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 6 Cores @ 2.00 GHz |
Cluster 2 | 2 Cores @ 2.60 GHz |
Memory Information | |
---|---|
Size | 7.31 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
169
31.4 IPS |
|
Image Classification (HP)
|
100% |
296
55.0 IPS |
|
Image Classification (Q)
|
99% |
283
52.7 IPS |
|
Image Segmentation (SP)
|
100% |
245
3.97 IPS |
|
Image Segmentation (HP)
|
100% |
418
6.78 IPS |
|
Image Segmentation (Q)
|
98% |
397
6.45 IPS |
|
Pose Estimation (SP)
|
100% |
163
0.19 IPS |
|
Pose Estimation (HP)
|
100% |
190
0.22 IPS |
|
Pose Estimation (Q)
|
96% |
189
0.22 IPS |
|
Object Detection (SP)
|
100% |
147
11.6 IPS |
|
Object Detection (HP)
|
100% |
243
19.3 IPS |
|
Object Detection (Q)
|
83% |
233
18.8 IPS |
|
Face Detection (SP)
|
100% |
581
6.91 IPS |
|
Face Detection (HP)
|
100% |
865
10.3 IPS |
|
Face Detection (Q)
|
97% |
804
9.59 IPS |
|
Depth Estimation (SP)
|
100% |
312
2.41 IPS |
|
Depth Estimation (HP)
|
99% |
403
3.11 IPS |
|
Depth Estimation (Q)
|
62% |
326
3.09 IPS |
|
Style Transfer (SP)
|
100% |
628
0.81 IPS |
|
Style Transfer (HP)
|
100% |
883
1.14 IPS |
|
Style Transfer (Q)
|
98% |
880
1.14 IPS |
|
Image Super-Resolution (SP)
|
100% |
160
5.90 IPS |
|
Image Super-Resolution (HP)
|
100% |
251
9.26 IPS |
|
Image Super-Resolution (Q)
|
97% |
247
9.15 IPS |
|
Text Classification (SP)
|
100% |
191
255.1 IPS |
|
Text Classification (HP)
|
100% |
188
250.4 IPS |
|
Text Classification (Q)
|
91% |
369
496.3 IPS |
|
Machine Translation (SP)
|
100% |
319
5.49 IPS |
|
Machine Translation (HP)
|
100% |
320
5.51 IPS |
|
Machine Translation (Q)
|
57% |
304
7.42 IPS |