Upload Date | May 14 2025 06:17 AM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Qualcomm ARMv8 |
System Information | |
---|---|
Operating System | Android 13 |
Model | DTResearch DA323EO |
Model ID | DTResearch DA323EO |
Motherboard | trinket |
Governor | walt |
CPU Information | |
---|---|
Name | Qualcomm ARMv8 |
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 | 7.43 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
148
27.5 IPS |
|
Image Classification (HP)
|
100% |
152
28.2 IPS |
|
Image Classification (Q)
|
100% |
229
42.6 IPS |
|
Image Segmentation (SP)
|
100% |
187
3.04 IPS |
|
Image Segmentation (HP)
|
100% |
179
2.91 IPS |
|
Image Segmentation (Q)
|
98% |
308
5.02 IPS |
|
Pose Estimation (SP)
|
100% |
707
0.83 IPS |
|
Pose Estimation (HP)
|
100% |
677
0.79 IPS |
|
Pose Estimation (Q)
|
84% |
694
0.82 IPS |
|
Object Detection (SP)
|
100% |
152
12.0 IPS |
|
Object Detection (HP)
|
100% |
152
12.1 IPS |
|
Object Detection (Q)
|
83% |
231
18.6 IPS |
|
Face Detection (SP)
|
100% |
361
4.29 IPS |
|
Face Detection (HP)
|
100% |
363
4.31 IPS |
|
Face Detection (Q)
|
95% |
551
6.58 IPS |
|
Depth Estimation (SP)
|
100% |
317
2.44 IPS |
|
Depth Estimation (HP)
|
99% |
342
2.64 IPS |
|
Depth Estimation (Q)
|
64% |
560
5.13 IPS |
|
Style Transfer (SP)
|
89% |
1376
1.79 IPS |
|
Style Transfer (HP)
|
89% |
1379
1.79 IPS |
|
Style Transfer (Q)
|
98% |
1569
2.02 IPS |
|
Image Super-Resolution (SP)
|
100% |
248
9.15 IPS |
|
Image Super-Resolution (HP)
|
100% |
249
9.20 IPS |
|
Image Super-Resolution (Q)
|
97% |
324
12.0 IPS |
|
Text Classification (SP)
|
100% |
147
196.0 IPS |
|
Text Classification (HP)
|
100% |
145
193.2 IPS |
|
Text Classification (Q)
|
88% |
152
205.3 IPS |
|
Machine Translation (SP)
|
100% |
185
3.18 IPS |
|
Machine Translation (HP)
|
100% |
183
3.15 IPS |
|
Machine Translation (Q)
|
50% |
86
3.05 IPS |