Upload Date | November 26 2024 07:22 PM |
Views | 22 |
AI Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | MediaTek Dimensity 7200 Pro |
System Information | |
---|---|
Operating System | Android 14 |
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% |
373
69.4 IPS |
|
Image Classification (HP)
|
100% |
1446
268.9 IPS |
|
Image Classification (Q)
|
99% |
3983
742.8 IPS |
|
Image Segmentation (SP)
|
100% |
320
5.19 IPS |
|
Image Segmentation (HP)
|
100% |
1545
25.0 IPS |
|
Image Segmentation (Q)
|
98% |
1114
18.1 IPS |
|
Pose Estimation (SP)
|
100% |
2180
2.54 IPS |
|
Pose Estimation (HP)
|
100% |
6344
7.40 IPS |
|
Pose Estimation (Q)
|
95% |
25620
30.0 IPS |
|
Object Detection (SP)
|
100% |
277
22.0 IPS |
|
Object Detection (HP)
|
100% |
1348
106.9 IPS |
|
Object Detection (Q)
|
86% |
2156
173.4 IPS |
|
Face Detection (SP)
|
28% |
71
13.2 IPS |
|
Face Detection (HP)
|
100% |
3561
42.3 IPS |
|
Face Detection (Q)
|
97% |
6833
81.5 IPS |
|
Depth Estimation (SP)
|
100% |
600
4.62 IPS |
|
Depth Estimation (HP)
|
99% |
6670
51.4 IPS |
|
Depth Estimation (Q)
|
62% |
13976
132.7 IPS |
|
Style Transfer (SP)
|
100% |
1114
1.43 IPS |
|
Style Transfer (HP)
|
100% |
477
0.61 IPS |
|
Style Transfer (Q)
|
30% |
445
6.71 IPS |
|
Image Super-Resolution (SP)
|
100% |
788
29.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
3978
146.9 IPS |
|
Image Super-Resolution (Q)
|
41% |
2699
393.1 IPS |
|
Text Classification (SP)
|
100% |
109
145.3 IPS |
|
Text Classification (HP)
|
100% |
211
281.0 IPS |
|
Text Classification (Q)
|
93% |
782
1.05 KIPS |
|
Machine Translation (SP)
|
100% |
258
4.44 IPS |
|
Machine Translation (HP)
|
100% |
315
5.43 IPS |
|
Machine Translation (Q)
|
60% |
284
6.39 IPS |