Upload Date | December 26 2024 04:16 AM |
Views | 1 |
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% |
127
23.5 IPS |
|
Image Classification (HP)
|
100% |
118
21.9 IPS |
|
Image Classification (Q)
|
100% |
216
40.1 IPS |
|
Image Segmentation (SP)
|
100% |
152
2.46 IPS |
|
Image Segmentation (HP)
|
100% |
154
2.50 IPS |
|
Image Segmentation (Q)
|
98% |
262
4.26 IPS |
|
Pose Estimation (SP)
|
100% |
593
0.69 IPS |
|
Pose Estimation (HP)
|
100% |
598
0.70 IPS |
|
Pose Estimation (Q)
|
84% |
526
0.62 IPS |
|
Object Detection (SP)
|
100% |
124
9.81 IPS |
|
Object Detection (HP)
|
100% |
128
10.2 IPS |
|
Object Detection (Q)
|
83% |
173
13.9 IPS |
|
Face Detection (SP)
|
100% |
340
4.04 IPS |
|
Face Detection (HP)
|
100% |
339
4.03 IPS |
|
Face Detection (Q)
|
95% |
536
6.40 IPS |
|
Depth Estimation (SP)
|
100% |
481
3.71 IPS |
|
Depth Estimation (HP)
|
99% |
447
3.44 IPS |
|
Depth Estimation (Q)
|
64% |
546
5.00 IPS |
|
Style Transfer (SP)
|
89% |
1191
1.55 IPS |
|
Style Transfer (HP)
|
89% |
1187
1.54 IPS |
|
Style Transfer (Q)
|
98% |
972
1.25 IPS |
|
Image Super-Resolution (SP)
|
100% |
240
8.85 IPS |
|
Image Super-Resolution (HP)
|
100% |
204
7.54 IPS |
|
Image Super-Resolution (Q)
|
97% |
230
8.52 IPS |
|
Text Classification (SP)
|
100% |
113
151.3 IPS |
|
Text Classification (HP)
|
100% |
110
147.0 IPS |
|
Text Classification (Q)
|
88% |
127
170.7 IPS |
|
Machine Translation (SP)
|
100% |
169
2.91 IPS |
|
Machine Translation (HP)
|
100% |
169
2.91 IPS |
|
Machine Translation (Q)
|
50% |
77
2.75 IPS |