Upload Date | June 22 2025 04:45 AM |
Views | 2 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | MediaTek Dimensity 7200 Pro |
System Information | |
---|---|
Operating System | Android 15 |
Model | Nothing Phone (2a) |
Model ID | Nothing A142 |
Motherboard | Pacman |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3405 revision 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 6 Cores @ 2.00 GHz |
Cluster 2 | 2 Cores @ 2.80 GHz |
Memory Information | |
---|---|
Size | 7.24 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
376
70.0 IPS |
|
Image Classification (HP)
|
100% |
1491
277.2 IPS |
|
Image Classification (Q)
|
99% |
4243
791.4 IPS |
|
Image Segmentation (SP)
|
100% |
319
5.17 IPS |
|
Image Segmentation (HP)
|
100% |
1521
24.7 IPS |
|
Image Segmentation (Q)
|
98% |
1113
18.1 IPS |
|
Pose Estimation (SP)
|
100% |
2181
2.54 IPS |
|
Pose Estimation (HP)
|
100% |
6340
7.40 IPS |
|
Pose Estimation (Q)
|
95% |
25598
30.0 IPS |
|
Object Detection (SP)
|
100% |
273
21.6 IPS |
|
Object Detection (HP)
|
100% |
1351
107.1 IPS |
|
Object Detection (Q)
|
86% |
2195
176.5 IPS |
|
Face Detection (SP)
|
28% |
71
13.2 IPS |
|
Face Detection (HP)
|
100% |
3542
42.1 IPS |
|
Face Detection (Q)
|
97% |
6775
80.8 IPS |
|
Depth Estimation (SP)
|
100% |
540
4.16 IPS |
|
Depth Estimation (HP)
|
99% |
6654
51.3 IPS |
|
Depth Estimation (Q)
|
62% |
14003
133.0 IPS |
|
Style Transfer (SP)
|
100% |
1060
1.36 IPS |
|
Style Transfer (HP)
|
100% |
410
0.53 IPS |
|
Style Transfer (Q)
|
30% |
370
5.58 IPS |
|
Image Super-Resolution (SP)
|
100% |
795
29.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
3975
146.8 IPS |
|
Image Super-Resolution (Q)
|
41% |
2752
400.8 IPS |
|
Text Classification (SP)
|
100% |
109
145.8 IPS |
|
Text Classification (HP)
|
100% |
174
231.6 IPS |
|
Text Classification (Q)
|
93% |
785
1.05 KIPS |
|
Machine Translation (SP)
|
100% |
229
3.95 IPS |
|
Machine Translation (HP)
|
100% |
236
4.07 IPS |
|
Machine Translation (Q)
|
60% |
253
5.69 IPS |