Upload Date | December 28 2024 05:13 AM |
Views | 3 |
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% |
111
20.6 IPS |
|
Image Classification (HP)
|
100% |
105
19.5 IPS |
|
Image Classification (Q)
|
100% |
176
32.8 IPS |
|
Image Segmentation (SP)
|
100% |
148
2.39 IPS |
|
Image Segmentation (HP)
|
100% |
158
2.57 IPS |
|
Image Segmentation (Q)
|
98% |
243
3.94 IPS |
|
Pose Estimation (SP)
|
100% |
580
0.68 IPS |
|
Pose Estimation (HP)
|
100% |
550
0.64 IPS |
|
Pose Estimation (Q)
|
84% |
486
0.58 IPS |
|
Object Detection (SP)
|
100% |
106
8.37 IPS |
|
Object Detection (HP)
|
100% |
128
10.2 IPS |
|
Object Detection (Q)
|
83% |
195
15.7 IPS |
|
Face Detection (SP)
|
100% |
291
3.46 IPS |
|
Face Detection (HP)
|
100% |
313
3.72 IPS |
|
Face Detection (Q)
|
95% |
446
5.33 IPS |
|
Depth Estimation (SP)
|
100% |
433
3.34 IPS |
|
Depth Estimation (HP)
|
99% |
396
3.05 IPS |
|
Depth Estimation (Q)
|
64% |
437
4.01 IPS |
|
Style Transfer (SP)
|
89% |
1071
1.39 IPS |
|
Style Transfer (HP)
|
89% |
1064
1.38 IPS |
|
Style Transfer (Q)
|
98% |
1296
1.67 IPS |
|
Image Super-Resolution (SP)
|
100% |
207
7.65 IPS |
|
Image Super-Resolution (HP)
|
100% |
212
7.84 IPS |
|
Image Super-Resolution (Q)
|
97% |
264
9.77 IPS |
|
Text Classification (SP)
|
100% |
120
160.4 IPS |
|
Text Classification (HP)
|
100% |
110
146.7 IPS |
|
Text Classification (Q)
|
88% |
117
157.9 IPS |
|
Machine Translation (SP)
|
100% |
158
2.72 IPS |
|
Machine Translation (HP)
|
100% |
169
2.90 IPS |
|
Machine Translation (Q)
|
50% |
77
2.72 IPS |