Upload Date | August 22 2024 09:51 PM |
Views | 1 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Qualcomm Snapdragon 670 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Samsung Galaxy Tab S5e |
Model ID | samsung SM-T720 |
Motherboard | sdm710 |
Governor | schedutil |
CPU Information | |
---|---|
Name | Qualcomm Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 6 part 2050 revision 13 |
Base Frequency | 1.71 GHz |
Cluster 1 | 6 Cores @ 1.71 GHz |
Cluster 2 | 2 Cores @ 2.00 GHz |
Memory Information | |
---|---|
Size | 3.56 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
61
11.3 IPS |
|
Image Classification (HP)
|
100% |
103
19.1 IPS |
|
Image Classification (Q)
|
97% |
107
20.0 IPS |
|
Image Segmentation (SP)
|
100% |
71
1.15 IPS |
|
Image Segmentation (HP)
|
100% |
115
1.87 IPS |
|
Image Segmentation (Q)
|
98% |
125
2.03 IPS |
|
Pose Estimation (SP)
|
100% |
117
0.14 IPS |
|
Pose Estimation (HP)
|
100% |
185
0.22 IPS |
|
Pose Estimation (Q)
|
95% |
184
0.22 IPS |
|
Object Detection (SP)
|
100% |
53
4.24 IPS |
|
Object Detection (HP)
|
100% |
84
6.69 IPS |
|
Object Detection (Q)
|
86% |
87
7.00 IPS |
|
Face Detection (SP)
|
100% |
144
1.71 IPS |
|
Face Detection (HP)
|
100% |
259
3.08 IPS |
|
Face Detection (Q)
|
97% |
272
3.24 IPS |
|
Depth Estimation (SP)
|
100% |
145
1.12 IPS |
|
Depth Estimation (HP)
|
99% |
266
2.05 IPS |
|
Depth Estimation (Q)
|
75% |
255
2.06 IPS |
|
Style Transfer (SP)
|
100% |
277
0.36 IPS |
|
Style Transfer (HP)
|
100% |
634
0.82 IPS |
|
Style Transfer (Q)
|
98% |
631
0.81 IPS |
|
Image Super-Resolution (SP)
|
100% |
71
2.61 IPS |
|
Image Super-Resolution (HP)
|
100% |
128
4.72 IPS |
|
Image Super-Resolution (Q)
|
97% |
126
4.68 IPS |
|
Text Classification (SP)
|
100% |
73
96.9 IPS |
|
Text Classification (HP)
|
100% |
73
97.0 IPS |
|
Text Classification (Q)
|
91% |
84
112.5 IPS |
|
Machine Translation (SP)
|
100% |
129
2.23 IPS |
|
Machine Translation (HP)
|
100% |
129
2.22 IPS |
|
Machine Translation (Q)
|
57% |
77
1.87 IPS |