Upload Date | September 19 2024 06:37 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.0 |
Model | iPhone 15 Plus |
Model ID | iPhone15,5 |
Motherboard | D38AP |
CPU Information | |
---|---|
Name | Apple A16 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.46 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 5.53 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1458
271.1 IPS |
|
Image Classification (HP)
|
100% |
10099
1.88 KIPS |
|
Image Classification (Q)
|
97% |
12393
2.31 KIPS |
|
Image Segmentation (SP)
|
100% |
1469
23.8 IPS |
|
Image Segmentation (HP)
|
100% |
12041
195.2 IPS |
|
Image Segmentation (Q)
|
99% |
14070
228.1 IPS |
|
Pose Estimation (SP)
|
100% |
6329
7.39 IPS |
|
Pose Estimation (HP)
|
100% |
96291
112.4 IPS |
|
Pose Estimation (Q)
|
95% |
101564
119.0 IPS |
|
Object Detection (SP)
|
100% |
1556
123.4 IPS |
|
Object Detection (HP)
|
100% |
12825
1.02 KIPS |
|
Object Detection (Q)
|
91% |
14562
1.16 KIPS |
|
Face Detection (SP)
|
100% |
3280
39.0 IPS |
|
Face Detection (HP)
|
100% |
30834
366.4 IPS |
|
Face Detection (Q)
|
100% |
39276
466.7 IPS |
|
Depth Estimation (SP)
|
100% |
6008
46.3 IPS |
|
Depth Estimation (HP)
|
99% |
74437
573.5 IPS |
|
Depth Estimation (Q)
|
85% |
94449
738.4 IPS |
|
Style Transfer (SP)
|
100% |
9533
12.3 IPS |
|
Style Transfer (HP)
|
100% |
172867
222.2 IPS |
|
Style Transfer (Q)
|
96% |
173582
224.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
4129
152.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
32006
1.18 KIPS |
|
Image Super-Resolution (Q)
|
99% |
37193
1.37 KIPS |
|
Text Classification (SP)
|
100% |
2632
3.51 KIPS |
|
Text Classification (HP)
|
100% |
1979
2.64 KIPS |
|
Text Classification (Q)
|
93% |
2428
3.26 KIPS |
|
Machine Translation (SP)
|
100% |
3393
58.4 IPS |
|
Machine Translation (HP)
|
100% |
2272
39.1 IPS |
|
Machine Translation (Q)
|
98% |
2276
39.3 IPS |