Upload Date | December 26 2024 03:04 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.3 |
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% |
1399
260.2 IPS |
|
Image Classification (HP)
|
100% |
10527
1.96 KIPS |
|
Image Classification (Q)
|
97% |
12744
2.38 KIPS |
|
Image Segmentation (SP)
|
100% |
1434
23.2 IPS |
|
Image Segmentation (HP)
|
100% |
14775
239.5 IPS |
|
Image Segmentation (Q)
|
99% |
17716
287.2 IPS |
|
Pose Estimation (SP)
|
100% |
7102
8.29 IPS |
|
Pose Estimation (HP)
|
100% |
96971
113.1 IPS |
|
Pose Estimation (Q)
|
95% |
100871
118.2 IPS |
|
Object Detection (SP)
|
100% |
1589
126.0 IPS |
|
Object Detection (HP)
|
100% |
12777
1.01 KIPS |
|
Object Detection (Q)
|
91% |
15208
1.22 KIPS |
|
Face Detection (SP)
|
100% |
3074
36.5 IPS |
|
Face Detection (HP)
|
100% |
29962
356.0 IPS |
|
Face Detection (Q)
|
100% |
38472
457.1 IPS |
|
Depth Estimation (SP)
|
100% |
6149
47.4 IPS |
|
Depth Estimation (HP)
|
99% |
75065
578.3 IPS |
|
Depth Estimation (Q)
|
85% |
95798
749.0 IPS |
|
Style Transfer (SP)
|
100% |
18841
24.2 IPS |
|
Style Transfer (HP)
|
100% |
162951
209.5 IPS |
|
Style Transfer (Q)
|
96% |
168935
218.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
4207
155.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
31679
1.17 KIPS |
|
Image Super-Resolution (Q)
|
99% |
35481
1.31 KIPS |
|
Text Classification (SP)
|
100% |
2607
3.48 KIPS |
|
Text Classification (HP)
|
100% |
2611
3.49 KIPS |
|
Text Classification (Q)
|
93% |
1994
2.68 KIPS |
|
Machine Translation (SP)
|
100% |
3449
59.4 IPS |
|
Machine Translation (HP)
|
100% |
7477
128.8 IPS |
|
Machine Translation (Q)
|
98% |
8180
141.4 IPS |