Upload Date | December 25 2024 10:06 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.2 |
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% |
1698
315.7 IPS |
|
Image Classification (HP)
|
100% |
10888
2.02 KIPS |
|
Image Classification (Q)
|
97% |
14994
2.80 KIPS |
|
Image Segmentation (SP)
|
100% |
1600
25.9 IPS |
|
Image Segmentation (HP)
|
100% |
15739
255.1 IPS |
|
Image Segmentation (Q)
|
99% |
20853
338.0 IPS |
|
Pose Estimation (SP)
|
100% |
8312
9.70 IPS |
|
Pose Estimation (HP)
|
100% |
106087
123.8 IPS |
|
Pose Estimation (Q)
|
95% |
203345
238.3 IPS |
|
Object Detection (SP)
|
100% |
1809
143.5 IPS |
|
Object Detection (HP)
|
100% |
13756
1.09 KIPS |
|
Object Detection (Q)
|
91% |
19096
1.53 KIPS |
|
Face Detection (SP)
|
100% |
3163
37.6 IPS |
|
Face Detection (HP)
|
100% |
34724
412.6 IPS |
|
Face Detection (Q)
|
100% |
50420
599.1 IPS |
|
Depth Estimation (SP)
|
100% |
7107
54.8 IPS |
|
Depth Estimation (HP)
|
99% |
79695
614.0 IPS |
|
Depth Estimation (Q)
|
85% |
129299
1.01 KIPS |
|
Style Transfer (SP)
|
100% |
21047
27.1 IPS |
|
Style Transfer (HP)
|
100% |
205101
263.7 IPS |
|
Style Transfer (Q)
|
96% |
248243
320.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
5003
184.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
33631
1.24 KIPS |
|
Image Super-Resolution (Q)
|
99% |
56076
2.07 KIPS |
|
Text Classification (SP)
|
100% |
3199
4.27 KIPS |
|
Text Classification (HP)
|
100% |
2990
3.99 KIPS |
|
Text Classification (Q)
|
93% |
2767
3.71 KIPS |
|
Machine Translation (SP)
|
100% |
3096
53.3 IPS |
|
Machine Translation (HP)
|
100% |
6170
106.3 IPS |
|
Machine Translation (Q)
|
98% |
7669
132.5 IPS |