Upload Date | January 07 2025 03:09 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.3 |
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
319.8 IPS |
|
Image Classification (HP)
|
100% |
11616
2.16 KIPS |
|
Image Classification (Q)
|
97% |
15424
2.88 KIPS |
|
Image Segmentation (SP)
|
100% |
1696
27.5 IPS |
|
Image Segmentation (HP)
|
100% |
15559
252.2 IPS |
|
Image Segmentation (Q)
|
99% |
20900
338.8 IPS |
|
Pose Estimation (SP)
|
100% |
8061
9.41 IPS |
|
Pose Estimation (HP)
|
100% |
106542
124.3 IPS |
|
Pose Estimation (Q)
|
95% |
203708
238.8 IPS |
|
Object Detection (SP)
|
100% |
1816
144.1 IPS |
|
Object Detection (HP)
|
100% |
13708
1.09 KIPS |
|
Object Detection (Q)
|
91% |
18913
1.51 KIPS |
|
Face Detection (SP)
|
100% |
3167
37.6 IPS |
|
Face Detection (HP)
|
100% |
35142
417.6 IPS |
|
Face Detection (Q)
|
100% |
50462
599.6 IPS |
|
Depth Estimation (SP)
|
100% |
7055
54.4 IPS |
|
Depth Estimation (HP)
|
99% |
78328
603.5 IPS |
|
Depth Estimation (Q)
|
85% |
128416
1.00 KIPS |
|
Style Transfer (SP)
|
100% |
21266
27.3 IPS |
|
Style Transfer (HP)
|
100% |
205459
264.1 IPS |
|
Style Transfer (Q)
|
96% |
248759
321.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
5048
186.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
33396
1.23 KIPS |
|
Image Super-Resolution (Q)
|
99% |
59784
2.21 KIPS |
|
Text Classification (SP)
|
100% |
3207
4.28 KIPS |
|
Text Classification (HP)
|
100% |
1920
2.56 KIPS |
|
Text Classification (Q)
|
93% |
1639
2.20 KIPS |
|
Machine Translation (SP)
|
100% |
3131
53.9 IPS |
|
Machine Translation (HP)
|
100% |
6161
106.1 IPS |
|
Machine Translation (Q)
|
98% |
7362
127.2 IPS |