Upload Date | December 29 2024 04:34 AM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm Snapdragon 662 |
System Information | |
---|---|
Operating System | Android 12 |
Model | Samsung Galaxy Tab A7 |
Model ID | samsung SM-T500 |
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% |
153
28.4 IPS |
|
Image Classification (HP)
|
100% |
153
28.4 IPS |
|
Image Classification (Q)
|
100% |
228
42.4 IPS |
|
Image Segmentation (SP)
|
100% |
191
3.10 IPS |
|
Image Segmentation (HP)
|
100% |
193
3.12 IPS |
|
Image Segmentation (Q)
|
98% |
307
5.00 IPS |
|
Pose Estimation (SP)
|
100% |
725
0.85 IPS |
|
Pose Estimation (HP)
|
100% |
709
0.83 IPS |
|
Pose Estimation (Q)
|
84% |
665
0.79 IPS |
|
Object Detection (SP)
|
100% |
156
12.4 IPS |
|
Object Detection (HP)
|
100% |
155
12.3 IPS |
|
Object Detection (Q)
|
83% |
229
18.5 IPS |
|
Face Detection (SP)
|
100% |
379
4.50 IPS |
|
Face Detection (HP)
|
100% |
384
4.56 IPS |
|
Face Detection (Q)
|
95% |
564
6.73 IPS |
|
Depth Estimation (SP)
|
100% |
476
3.67 IPS |
|
Depth Estimation (HP)
|
99% |
516
3.98 IPS |
|
Depth Estimation (Q)
|
64% |
550
5.03 IPS |
|
Style Transfer (SP)
|
89% |
1446
1.88 IPS |
|
Style Transfer (HP)
|
89% |
1452
1.88 IPS |
|
Style Transfer (Q)
|
98% |
1611
2.08 IPS |
|
Image Super-Resolution (SP)
|
100% |
276
10.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
278
10.3 IPS |
|
Image Super-Resolution (Q)
|
97% |
343
12.7 IPS |
|
Text Classification (SP)
|
100% |
160
214.1 IPS |
|
Text Classification (HP)
|
100% |
154
205.1 IPS |
|
Text Classification (Q)
|
88% |
189
255.3 IPS |
|
Machine Translation (SP)
|
100% |
240
4.14 IPS |
|
Machine Translation (HP)
|
100% |
239
4.11 IPS |
|
Machine Translation (Q)
|
50% |
112
3.99 IPS |