Upload Date | September 17 2024 02:26 AM |
Views | 1 |
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% |
1720
319.9 IPS |
|
Image Classification (HP)
|
100% |
11205
2.08 KIPS |
|
Image Classification (Q)
|
97% |
15160
2.83 KIPS |
|
Image Segmentation (SP)
|
100% |
1602
26.0 IPS |
|
Image Segmentation (HP)
|
100% |
12787
207.3 IPS |
|
Image Segmentation (Q)
|
99% |
15990
259.2 IPS |
|
Pose Estimation (SP)
|
100% |
8406
9.81 IPS |
|
Pose Estimation (HP)
|
100% |
106738
124.5 IPS |
|
Pose Estimation (Q)
|
95% |
203048
238.0 IPS |
|
Object Detection (SP)
|
100% |
1797
142.6 IPS |
|
Object Detection (HP)
|
100% |
13559
1.08 KIPS |
|
Object Detection (Q)
|
91% |
18994
1.52 KIPS |
|
Face Detection (SP)
|
100% |
3142
37.3 IPS |
|
Face Detection (HP)
|
100% |
33348
396.2 IPS |
|
Face Detection (Q)
|
100% |
48736
579.1 IPS |
|
Depth Estimation (SP)
|
100% |
7221
55.6 IPS |
|
Depth Estimation (HP)
|
99% |
78114
601.8 IPS |
|
Depth Estimation (Q)
|
85% |
127456
996.5 IPS |
|
Style Transfer (SP)
|
100% |
21528
27.7 IPS |
|
Style Transfer (HP)
|
100% |
206252
265.1 IPS |
|
Style Transfer (Q)
|
96% |
248113
320.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
5043
186.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
34019
1.26 KIPS |
|
Image Super-Resolution (Q)
|
99% |
58170
2.15 KIPS |
|
Text Classification (SP)
|
100% |
3191
4.26 KIPS |
|
Text Classification (HP)
|
100% |
3028
4.04 KIPS |
|
Text Classification (Q)
|
93% |
3018
4.05 KIPS |
|
Machine Translation (SP)
|
100% |
3096
53.3 IPS |
|
Machine Translation (HP)
|
100% |
6157
106.1 IPS |
|
Machine Translation (Q)
|
98% |
7103
122.7 IPS |