Upload Date | September 18 2024 01:51 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.0 |
Model | iPhone 15 Pro Max |
Model ID | iPhone16,2 |
Motherboard | D84AP |
CPU Information | |
---|---|
Name | Apple A17 Pro |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.78 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.48 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1723
320.5 IPS |
|
Image Classification (HP)
|
100% |
10733
2.00 KIPS |
|
Image Classification (Q)
|
97% |
15247
2.85 KIPS |
|
Image Segmentation (SP)
|
100% |
1626
26.4 IPS |
|
Image Segmentation (HP)
|
100% |
12926
209.5 IPS |
|
Image Segmentation (Q)
|
99% |
16123
261.4 IPS |
|
Pose Estimation (SP)
|
100% |
8033
9.37 IPS |
|
Pose Estimation (HP)
|
100% |
106219
123.9 IPS |
|
Pose Estimation (Q)
|
95% |
202929
237.8 IPS |
|
Object Detection (SP)
|
100% |
1800
142.8 IPS |
|
Object Detection (HP)
|
100% |
13641
1.08 KIPS |
|
Object Detection (Q)
|
91% |
19173
1.53 KIPS |
|
Face Detection (SP)
|
100% |
3180
37.8 IPS |
|
Face Detection (HP)
|
100% |
33541
398.5 IPS |
|
Face Detection (Q)
|
100% |
49021
582.5 IPS |
|
Depth Estimation (SP)
|
100% |
7167
55.2 IPS |
|
Depth Estimation (HP)
|
99% |
79390
611.7 IPS |
|
Depth Estimation (Q)
|
85% |
128330
1.00 KIPS |
|
Style Transfer (SP)
|
100% |
21038
27.0 IPS |
|
Style Transfer (HP)
|
100% |
206754
265.8 IPS |
|
Style Transfer (Q)
|
96% |
247449
319.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
4975
183.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
35005
1.29 KIPS |
|
Image Super-Resolution (Q)
|
99% |
55059
2.03 KIPS |
|
Text Classification (SP)
|
100% |
3190
4.26 KIPS |
|
Text Classification (HP)
|
100% |
3338
4.46 KIPS |
|
Text Classification (Q)
|
93% |
3265
4.38 KIPS |
|
Machine Translation (SP)
|
100% |
3113
53.6 IPS |
|
Machine Translation (HP)
|
100% |
6198
106.8 IPS |
|
Machine Translation (Q)
|
98% |
7530
130.1 IPS |