User | riussi |
Upload Date | January 28 2025 04:50 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 18.2.1 |
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% |
1976
367.5 IPS |
|
Image Classification (HP)
|
100% |
15731
2.93 KIPS |
|
Image Classification (Q)
|
97% |
20416
3.81 KIPS |
|
Image Segmentation (SP)
|
100% |
1922
31.2 IPS |
|
Image Segmentation (HP)
|
100% |
18217
295.3 IPS |
|
Image Segmentation (Q)
|
99% |
24001
389.1 IPS |
|
Pose Estimation (SP)
|
100% |
7924
9.25 IPS |
|
Pose Estimation (HP)
|
100% |
149653
174.6 IPS |
|
Pose Estimation (Q)
|
95% |
293326
343.8 IPS |
|
Object Detection (SP)
|
100% |
2088
165.7 IPS |
|
Object Detection (HP)
|
100% |
16405
1.30 KIPS |
|
Object Detection (Q)
|
91% |
22637
1.81 KIPS |
|
Face Detection (SP)
|
100% |
3539
42.1 IPS |
|
Face Detection (HP)
|
100% |
41491
493.0 IPS |
|
Face Detection (Q)
|
100% |
59864
711.3 IPS |
|
Depth Estimation (SP)
|
100% |
7489
57.7 IPS |
|
Depth Estimation (HP)
|
99% |
86877
669.3 IPS |
|
Depth Estimation (Q)
|
85% |
159488
1.25 KIPS |
|
Style Transfer (SP)
|
100% |
22346
28.7 IPS |
|
Style Transfer (HP)
|
100% |
244645
314.5 IPS |
|
Style Transfer (Q)
|
96% |
302380
390.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
5421
200.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
49673
1.83 KIPS |
|
Image Super-Resolution (Q)
|
99% |
83878
3.10 KIPS |
|
Text Classification (SP)
|
100% |
3417
4.56 KIPS |
|
Text Classification (HP)
|
100% |
4772
6.37 KIPS |
|
Text Classification (Q)
|
93% |
5243
7.04 KIPS |
|
Machine Translation (SP)
|
100% |
3756
64.7 IPS |
|
Machine Translation (HP)
|
100% |
9286
160.0 IPS |
|
Machine Translation (Q)
|
98% |
11493
198.6 IPS |