Upload Date | January 04 2025 01:29 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.1 |
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% |
1415
263.1 IPS |
|
Image Classification (HP)
|
100% |
10604
1.97 KIPS |
|
Image Classification (Q)
|
97% |
12654
2.36 KIPS |
|
Image Segmentation (SP)
|
100% |
1453
23.6 IPS |
|
Image Segmentation (HP)
|
100% |
14770
239.4 IPS |
|
Image Segmentation (Q)
|
99% |
17922
290.5 IPS |
|
Pose Estimation (SP)
|
100% |
7005
8.17 IPS |
|
Pose Estimation (HP)
|
100% |
95285
111.2 IPS |
|
Pose Estimation (Q)
|
95% |
101555
119.0 IPS |
|
Object Detection (SP)
|
100% |
1574
124.9 IPS |
|
Object Detection (HP)
|
100% |
12878
1.02 KIPS |
|
Object Detection (Q)
|
91% |
14918
1.19 KIPS |
|
Face Detection (SP)
|
100% |
2951
35.1 IPS |
|
Face Detection (HP)
|
100% |
30179
358.6 IPS |
|
Face Detection (Q)
|
100% |
38919
462.4 IPS |
|
Depth Estimation (SP)
|
100% |
6222
47.9 IPS |
|
Depth Estimation (HP)
|
99% |
76783
591.6 IPS |
|
Depth Estimation (Q)
|
85% |
96749
756.4 IPS |
|
Style Transfer (SP)
|
100% |
18768
24.1 IPS |
|
Style Transfer (HP)
|
100% |
163917
210.7 IPS |
|
Style Transfer (Q)
|
96% |
167943
216.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
4189
154.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
31863
1.18 KIPS |
|
Image Super-Resolution (Q)
|
99% |
36615
1.35 KIPS |
|
Text Classification (SP)
|
100% |
2618
3.49 KIPS |
|
Text Classification (HP)
|
100% |
2274
3.04 KIPS |
|
Text Classification (Q)
|
93% |
1783
2.39 KIPS |
|
Machine Translation (SP)
|
100% |
3501
60.3 IPS |
|
Machine Translation (HP)
|
100% |
5567
95.9 IPS |
|
Machine Translation (Q)
|
98% |
5959
103.0 IPS |