Upload Date | September 18 2024 03:21 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 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% |
1398
260.0 IPS |
|
Image Classification (HP)
|
100% |
10620
1.98 KIPS |
|
Image Classification (Q)
|
97% |
11742
2.19 KIPS |
|
Image Segmentation (SP)
|
100% |
1436
23.3 IPS |
|
Image Segmentation (HP)
|
100% |
11652
188.9 IPS |
|
Image Segmentation (Q)
|
99% |
13656
221.4 IPS |
|
Pose Estimation (SP)
|
100% |
6937
8.09 IPS |
|
Pose Estimation (HP)
|
100% |
95579
111.5 IPS |
|
Pose Estimation (Q)
|
95% |
102140
119.7 IPS |
|
Object Detection (SP)
|
100% |
1572
124.7 IPS |
|
Object Detection (HP)
|
100% |
13040
1.03 KIPS |
|
Object Detection (Q)
|
91% |
14875
1.19 KIPS |
|
Face Detection (SP)
|
100% |
3095
36.8 IPS |
|
Face Detection (HP)
|
100% |
29910
355.4 IPS |
|
Face Detection (Q)
|
100% |
38748
460.4 IPS |
|
Depth Estimation (SP)
|
100% |
6260
48.2 IPS |
|
Depth Estimation (HP)
|
99% |
75352
580.5 IPS |
|
Depth Estimation (Q)
|
85% |
96776
756.6 IPS |
|
Style Transfer (SP)
|
100% |
18773
24.1 IPS |
|
Style Transfer (HP)
|
100% |
165602
212.9 IPS |
|
Style Transfer (Q)
|
96% |
170684
220.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
4217
155.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
35078
1.30 KIPS |
|
Image Super-Resolution (Q)
|
99% |
37556
1.39 KIPS |
|
Text Classification (SP)
|
100% |
2619
3.50 KIPS |
|
Text Classification (HP)
|
100% |
2076
2.77 KIPS |
|
Text Classification (Q)
|
93% |
2438
3.27 KIPS |
|
Machine Translation (SP)
|
100% |
3447
59.4 IPS |
|
Machine Translation (HP)
|
100% |
2402
41.4 IPS |
|
Machine Translation (Q)
|
98% |
2437
42.1 IPS |