Upload Date | May 14 2025 01:49 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.5 |
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% |
1672
310.9 IPS |
|
Image Classification (HP)
|
100% |
10951
2.04 KIPS |
|
Image Classification (Q)
|
97% |
15492
2.89 KIPS |
|
Image Segmentation (SP)
|
100% |
1579
25.6 IPS |
|
Image Segmentation (HP)
|
100% |
16678
270.4 IPS |
|
Image Segmentation (Q)
|
99% |
21108
342.2 IPS |
|
Pose Estimation (SP)
|
100% |
7666
8.94 IPS |
|
Pose Estimation (HP)
|
100% |
106302
124.0 IPS |
|
Pose Estimation (Q)
|
95% |
204791
240.0 IPS |
|
Object Detection (SP)
|
100% |
1770
140.4 IPS |
|
Object Detection (HP)
|
100% |
13925
1.10 KIPS |
|
Object Detection (Q)
|
91% |
18905
1.51 KIPS |
|
Face Detection (SP)
|
100% |
3027
36.0 IPS |
|
Face Detection (HP)
|
100% |
36585
434.7 IPS |
|
Face Detection (Q)
|
100% |
52603
625.0 IPS |
|
Depth Estimation (SP)
|
100% |
6835
52.7 IPS |
|
Depth Estimation (HP)
|
99% |
77859
599.9 IPS |
|
Depth Estimation (Q)
|
85% |
128120
1.00 KIPS |
|
Style Transfer (SP)
|
100% |
20814
26.8 IPS |
|
Style Transfer (HP)
|
100% |
198577
255.3 IPS |
|
Style Transfer (Q)
|
96% |
252709
326.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
4769
176.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
33843
1.25 KIPS |
|
Image Super-Resolution (Q)
|
99% |
57191
2.11 KIPS |
|
Text Classification (SP)
|
100% |
3293
4.40 KIPS |
|
Text Classification (HP)
|
100% |
3526
4.71 KIPS |
|
Text Classification (Q)
|
93% |
3578
4.80 KIPS |
|
Machine Translation (SP)
|
100% |
3159
54.4 IPS |
|
Machine Translation (HP)
|
100% |
6376
109.8 IPS |
|
Machine Translation (Q)
|
98% |
7742
133.8 IPS |