Upload Date | September 18 2024 02:24 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.0 |
Model | iPhone 14 Pro |
Model ID | iPhone15,2 |
Motherboard | D73AP |
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% |
1459
271.3 IPS |
|
Image Classification (HP)
|
100% |
10336
1.92 KIPS |
|
Image Classification (Q)
|
97% |
12023
2.24 KIPS |
|
Image Segmentation (SP)
|
100% |
1517
24.6 IPS |
|
Image Segmentation (HP)
|
100% |
11822
191.6 IPS |
|
Image Segmentation (Q)
|
99% |
13560
219.8 IPS |
|
Pose Estimation (SP)
|
100% |
6655
7.76 IPS |
|
Pose Estimation (HP)
|
100% |
96800
112.9 IPS |
|
Pose Estimation (Q)
|
95% |
102461
120.1 IPS |
|
Object Detection (SP)
|
100% |
1568
124.4 IPS |
|
Object Detection (HP)
|
100% |
12530
993.9 IPS |
|
Object Detection (Q)
|
91% |
15116
1.21 KIPS |
|
Face Detection (SP)
|
100% |
3168
37.6 IPS |
|
Face Detection (HP)
|
100% |
30782
365.8 IPS |
|
Face Detection (Q)
|
100% |
38418
456.5 IPS |
|
Depth Estimation (SP)
|
100% |
6239
48.1 IPS |
|
Depth Estimation (HP)
|
99% |
72678
559.9 IPS |
|
Depth Estimation (Q)
|
85% |
92454
722.8 IPS |
|
Style Transfer (SP)
|
100% |
18844
24.2 IPS |
|
Style Transfer (HP)
|
100% |
172264
221.4 IPS |
|
Style Transfer (Q)
|
96% |
172502
222.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
4228
156.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
31838
1.18 KIPS |
|
Image Super-Resolution (Q)
|
99% |
37032
1.37 KIPS |
|
Text Classification (SP)
|
100% |
2648
3.53 KIPS |
|
Text Classification (HP)
|
100% |
2309
3.08 KIPS |
|
Text Classification (Q)
|
93% |
2828
3.80 KIPS |
|
Machine Translation (SP)
|
100% |
3610
62.2 IPS |
|
Machine Translation (HP)
|
100% |
2350
40.5 IPS |
|
Machine Translation (Q)
|
98% |
2258
39.0 IPS |