User | Kiruno |
Upload Date | December 10 2024 01:59 PM |
Views | 11 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 18.2 |
Model | iPhone 16 Pro Max |
Model ID | iPhone17,2 |
Motherboard | D94AP |
CPU Information | |
---|---|
Name | Apple A18 Pro |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 4.04 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.45 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1989
369.9 IPS |
|
Image Classification (HP)
|
100% |
15201
2.83 KIPS |
|
Image Classification (Q)
|
97% |
20196
3.77 KIPS |
|
Image Segmentation (SP)
|
100% |
1911
31.0 IPS |
|
Image Segmentation (HP)
|
100% |
18300
296.7 IPS |
|
Image Segmentation (Q)
|
99% |
24009
389.2 IPS |
|
Pose Estimation (SP)
|
100% |
8165
9.53 IPS |
|
Pose Estimation (HP)
|
100% |
146005
170.4 IPS |
|
Pose Estimation (Q)
|
95% |
292075
342.3 IPS |
|
Object Detection (SP)
|
100% |
2073
164.4 IPS |
|
Object Detection (HP)
|
100% |
16575
1.31 KIPS |
|
Object Detection (Q)
|
91% |
22790
1.82 KIPS |
|
Face Detection (SP)
|
100% |
3404
40.4 IPS |
|
Face Detection (HP)
|
100% |
41166
489.1 IPS |
|
Face Detection (Q)
|
100% |
57350
681.4 IPS |
|
Depth Estimation (SP)
|
100% |
7335
56.5 IPS |
|
Depth Estimation (HP)
|
99% |
94686
729.5 IPS |
|
Depth Estimation (Q)
|
85% |
161007
1.26 KIPS |
|
Style Transfer (SP)
|
100% |
22432
28.8 IPS |
|
Style Transfer (HP)
|
100% |
243803
313.4 IPS |
|
Style Transfer (Q)
|
96% |
301285
388.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
5228
193.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
49301
1.82 KIPS |
|
Image Super-Resolution (Q)
|
99% |
85412
3.15 KIPS |
|
Text Classification (SP)
|
100% |
3407
4.55 KIPS |
|
Text Classification (HP)
|
100% |
4734
6.32 KIPS |
|
Text Classification (Q)
|
93% |
4497
6.04 KIPS |
|
Machine Translation (SP)
|
100% |
3733
64.3 IPS |
|
Machine Translation (HP)
|
100% |
9160
157.8 IPS |
|
Machine Translation (Q)
|
98% |
11276
194.9 IPS |