Upload Date | October 11 2024 02:27 AM |
Views | 26 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | ARM ARMv8 |
System Information | |
---|---|
Operating System | Android 14 |
Model | Wingtech TMRV075G |
Model ID | Wingtech TMRV075G |
Motherboard | S88523AA1 |
Governor | walt |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 2 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 4 Cores @ 2.21 GHz |
Memory Information | |
---|---|
Size | 5.32 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
124
23.1 IPS |
|
Image Classification (HP)
|
100% |
213
39.7 IPS |
|
Image Classification (Q)
|
97% |
201
37.6 IPS |
|
Image Segmentation (SP)
|
100% |
204
3.31 IPS |
|
Image Segmentation (HP)
|
100% |
278
4.51 IPS |
|
Image Segmentation (Q)
|
98% |
269
4.37 IPS |
|
Pose Estimation (SP)
|
100% |
175
0.20 IPS |
|
Pose Estimation (HP)
|
100% |
281
0.33 IPS |
|
Pose Estimation (Q)
|
95% |
280
0.33 IPS |
|
Object Detection (SP)
|
100% |
98
7.76 IPS |
|
Object Detection (HP)
|
100% |
144
11.4 IPS |
|
Object Detection (Q)
|
89% |
142
11.4 IPS |
|
Face Detection (SP)
|
100% |
364
4.33 IPS |
|
Face Detection (HP)
|
100% |
509
6.05 IPS |
|
Face Detection (Q)
|
97% |
476
5.68 IPS |
|
Depth Estimation (SP)
|
100% |
272
2.10 IPS |
|
Depth Estimation (HP)
|
99% |
457
3.53 IPS |
|
Depth Estimation (Q)
|
63% |
360
3.38 IPS |
|
Style Transfer (SP)
|
100% |
600
0.77 IPS |
|
Style Transfer (HP)
|
100% |
1196
1.54 IPS |
|
Style Transfer (Q)
|
98% |
1207
1.56 IPS |
|
Image Super-Resolution (SP)
|
100% |
108
4.00 IPS |
|
Image Super-Resolution (HP)
|
100% |
135
4.98 IPS |
|
Image Super-Resolution (Q)
|
97% |
133
4.92 IPS |
|
Text Classification (SP)
|
100% |
154
205.1 IPS |
|
Text Classification (HP)
|
100% |
154
205.1 IPS |
|
Text Classification (Q)
|
91% |
293
393.2 IPS |
|
Machine Translation (SP)
|
100% |
261
4.49 IPS |
|
Machine Translation (HP)
|
100% |
260
4.48 IPS |
|
Machine Translation (Q)
|
57% |
242
5.90 IPS |