Upload Date | April 24 2025 08:51 PM |
Views | 3 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm Qualcomm |
System Information | |
---|---|
Operating System | Android 12 |
Model | samsung SM-T505N |
Model ID | samsung SM-T505N |
Motherboard | bengal |
Governor | schedutil |
CPU Information | |
---|---|
Name | Qualcomm Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 10 part 2048 revision 2 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 4 Cores @ 2.02 GHz |
Memory Information | |
---|---|
Size | 2.64 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
141
26.2 IPS |
|
Image Classification (HP)
|
100% |
150
27.9 IPS |
|
Image Classification (Q)
|
100% |
227
42.3 IPS |
|
Image Segmentation (SP)
|
100% |
189
3.06 IPS |
|
Image Segmentation (HP)
|
100% |
190
3.08 IPS |
|
Image Segmentation (Q)
|
98% |
308
5.02 IPS |
|
Pose Estimation (SP)
|
100% |
726
0.85 IPS |
|
Pose Estimation (HP)
|
100% |
724
0.85 IPS |
|
Pose Estimation (Q)
|
84% |
671
0.80 IPS |
|
Object Detection (SP)
|
100% |
155
12.3 IPS |
|
Object Detection (HP)
|
100% |
158
12.5 IPS |
|
Object Detection (Q)
|
83% |
234
18.9 IPS |
|
Face Detection (SP)
|
100% |
386
4.58 IPS |
|
Face Detection (HP)
|
100% |
377
4.48 IPS |
|
Face Detection (Q)
|
95% |
572
6.82 IPS |
|
Depth Estimation (SP)
|
100% |
479
3.69 IPS |
|
Depth Estimation (HP)
|
99% |
523
4.03 IPS |
|
Depth Estimation (Q)
|
64% |
559
5.12 IPS |
|
Style Transfer (SP)
|
89% |
1447
1.88 IPS |
|
Style Transfer (HP)
|
89% |
1456
1.89 IPS |
|
Style Transfer (Q)
|
98% |
1622
2.09 IPS |
|
Image Super-Resolution (SP)
|
100% |
277
10.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
265
9.80 IPS |
|
Image Super-Resolution (Q)
|
97% |
340
12.6 IPS |
|
Text Classification (SP)
|
100% |
155
207.6 IPS |
|
Text Classification (HP)
|
100% |
154
205.5 IPS |
|
Text Classification (Q)
|
88% |
170
229.3 IPS |
|
Machine Translation (SP)
|
100% |
200
3.44 IPS |
|
Machine Translation (HP)
|
100% |
199
3.43 IPS |
|
Machine Translation (Q)
|
50% |
101
3.57 IPS |