Upload Date | September 17 2024 03:39 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.0 |
Model | iPhone 14 Pro Max |
Model ID | iPhone15,3 |
Motherboard | D74AP |
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 | 5.51 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1432
266.3 IPS |
|
Image Classification (HP)
|
100% |
9998
1.86 KIPS |
|
Image Classification (Q)
|
97% |
12128
2.26 KIPS |
|
Image Segmentation (SP)
|
100% |
1431
23.2 IPS |
|
Image Segmentation (HP)
|
100% |
11497
186.4 IPS |
|
Image Segmentation (Q)
|
99% |
13713
222.3 IPS |
|
Pose Estimation (SP)
|
100% |
7090
8.27 IPS |
|
Pose Estimation (HP)
|
100% |
95079
110.9 IPS |
|
Pose Estimation (Q)
|
95% |
102253
119.8 IPS |
|
Object Detection (SP)
|
100% |
1580
125.3 IPS |
|
Object Detection (HP)
|
100% |
12989
1.03 KIPS |
|
Object Detection (Q)
|
91% |
14729
1.18 KIPS |
|
Face Detection (SP)
|
100% |
3099
36.8 IPS |
|
Face Detection (HP)
|
100% |
29843
354.6 IPS |
|
Face Detection (Q)
|
100% |
37949
450.9 IPS |
|
Depth Estimation (SP)
|
100% |
6210
47.8 IPS |
|
Depth Estimation (HP)
|
99% |
74497
574.0 IPS |
|
Depth Estimation (Q)
|
85% |
94843
741.5 IPS |
|
Style Transfer (SP)
|
100% |
18857
24.2 IPS |
|
Style Transfer (HP)
|
100% |
166376
213.9 IPS |
|
Style Transfer (Q)
|
96% |
168047
216.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
4211
155.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
31337
1.16 KIPS |
|
Image Super-Resolution (Q)
|
99% |
36890
1.36 KIPS |
|
Text Classification (SP)
|
100% |
2605
3.48 KIPS |
|
Text Classification (HP)
|
100% |
2080
2.78 KIPS |
|
Text Classification (Q)
|
93% |
1959
2.63 KIPS |
|
Machine Translation (SP)
|
100% |
3429
59.1 IPS |
|
Machine Translation (HP)
|
100% |
2397
41.3 IPS |
|
Machine Translation (Q)
|
98% |
2390
41.3 IPS |