Upload Date | December 04 2024 06:43 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% |
128
23.9 IPS |
|
Image Classification (HP)
|
100% |
130
24.2 IPS |
|
Image Classification (Q)
|
100% |
217
40.4 IPS |
|
Image Segmentation (SP)
|
100% |
173
2.81 IPS |
|
Image Segmentation (HP)
|
100% |
174
2.83 IPS |
|
Image Segmentation (Q)
|
98% |
299
4.86 IPS |
|
Pose Estimation (SP)
|
100% |
640
0.75 IPS |
|
Pose Estimation (HP)
|
100% |
618
0.72 IPS |
|
Pose Estimation (Q)
|
84% |
617
0.73 IPS |
|
Object Detection (SP)
|
100% |
140
11.1 IPS |
|
Object Detection (HP)
|
100% |
141
11.2 IPS |
|
Object Detection (Q)
|
83% |
226
18.2 IPS |
|
Face Detection (SP)
|
100% |
342
4.07 IPS |
|
Face Detection (HP)
|
100% |
321
3.81 IPS |
|
Face Detection (Q)
|
95% |
544
6.50 IPS |
|
Depth Estimation (SP)
|
100% |
467
3.60 IPS |
|
Depth Estimation (HP)
|
99% |
469
3.61 IPS |
|
Depth Estimation (Q)
|
64% |
547
5.01 IPS |
|
Style Transfer (SP)
|
89% |
1329
1.73 IPS |
|
Style Transfer (HP)
|
89% |
1156
1.50 IPS |
|
Style Transfer (Q)
|
98% |
1554
2.00 IPS |
|
Image Super-Resolution (SP)
|
100% |
252
9.29 IPS |
|
Image Super-Resolution (HP)
|
100% |
185
6.82 IPS |
|
Image Super-Resolution (Q)
|
97% |
295
10.9 IPS |
|
Text Classification (SP)
|
100% |
135
180.7 IPS |
|
Text Classification (HP)
|
100% |
129
172.8 IPS |
|
Text Classification (Q)
|
88% |
153
206.0 IPS |
|
Machine Translation (SP)
|
100% |
175
3.02 IPS |
|
Machine Translation (HP)
|
100% |
175
3.02 IPS |
|
Machine Translation (Q)
|
50% |
87
3.10 IPS |