User | Vaitek |
Upload Date | August 18 2024 07:36 AM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Qualcomm Qualcomm |
System Information | |
---|---|
Operating System | Android 13 |
Model | realme RMX3081 |
Model ID | realme RMX3081 |
Motherboard | atoll |
Governor | schedutil |
CPU Information | |
---|---|
Name | Qualcomm Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 15 part 2052 revision 15 |
Base Frequency | 1.80 GHz |
Cluster 1 | 6 Cores @ 1.80 GHz |
Cluster 2 | 2 Cores @ 2.32 GHz |
Memory Information | |
---|---|
Size | 5.34 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
101
18.8 IPS |
|
Image Classification (HP)
|
100% |
162
30.2 IPS |
|
Image Classification (Q)
|
97% |
171
31.9 IPS |
|
Image Segmentation (SP)
|
100% |
114
1.84 IPS |
|
Image Segmentation (HP)
|
100% |
172
2.78 IPS |
|
Image Segmentation (Q)
|
98% |
180
2.93 IPS |
|
Pose Estimation (SP)
|
100% |
201
0.23 IPS |
|
Pose Estimation (HP)
|
100% |
276
0.32 IPS |
|
Pose Estimation (Q)
|
95% |
273
0.32 IPS |
|
Object Detection (SP)
|
100% |
89
7.03 IPS |
|
Object Detection (HP)
|
100% |
129
10.2 IPS |
|
Object Detection (Q)
|
86% |
133
10.7 IPS |
|
Face Detection (SP)
|
100% |
233
2.77 IPS |
|
Face Detection (HP)
|
100% |
410
4.87 IPS |
|
Face Detection (Q)
|
97% |
416
4.96 IPS |
|
Depth Estimation (SP)
|
100% |
241
1.85 IPS |
|
Depth Estimation (HP)
|
99% |
409
3.15 IPS |
|
Depth Estimation (Q)
|
75% |
390
3.15 IPS |
|
Style Transfer (SP)
|
100% |
473
0.61 IPS |
|
Style Transfer (HP)
|
100% |
1012
1.30 IPS |
|
Style Transfer (Q)
|
98% |
1000
1.29 IPS |
|
Image Super-Resolution (SP)
|
100% |
120
4.42 IPS |
|
Image Super-Resolution (HP)
|
100% |
196
7.23 IPS |
|
Image Super-Resolution (Q)
|
97% |
193
7.14 IPS |
|
Text Classification (SP)
|
100% |
163
217.1 IPS |
|
Text Classification (HP)
|
100% |
162
216.0 IPS |
|
Text Classification (Q)
|
91% |
271
364.3 IPS |
|
Machine Translation (SP)
|
100% |
266
4.58 IPS |
|
Machine Translation (HP)
|
100% |
272
4.68 IPS |
|
Machine Translation (Q)
|
57% |
213
5.21 IPS |