User | M91 |
Upload Date | October 27 2024 09:35 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.1 |
Model | iPhone 14 Pro Max |
Model ID | iPhone15,3 |
Motherboard | D74AP |
CPU Information | |
---|---|
Name | Apple A16 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.46 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 5.51 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1435
266.9 IPS |
|
Image Classification (HP)
|
100% |
10442
1.94 KIPS |
|
Image Classification (Q)
|
97% |
12714
2.37 KIPS |
|
Image Segmentation (SP)
|
100% |
1428
23.2 IPS |
|
Image Segmentation (HP)
|
100% |
14946
242.3 IPS |
|
Image Segmentation (Q)
|
99% |
17936
290.8 IPS |
|
Pose Estimation (SP)
|
100% |
6606
7.71 IPS |
|
Pose Estimation (HP)
|
100% |
94417
110.2 IPS |
|
Pose Estimation (Q)
|
95% |
101574
119.1 IPS |
|
Object Detection (SP)
|
100% |
1575
125.0 IPS |
|
Object Detection (HP)
|
100% |
12435
986.4 IPS |
|
Object Detection (Q)
|
91% |
14386
1.15 KIPS |
|
Face Detection (SP)
|
100% |
3116
37.0 IPS |
|
Face Detection (HP)
|
100% |
30795
365.9 IPS |
|
Face Detection (Q)
|
100% |
39458
468.9 IPS |
|
Depth Estimation (SP)
|
100% |
6246
48.1 IPS |
|
Depth Estimation (HP)
|
99% |
75213
579.5 IPS |
|
Depth Estimation (Q)
|
85% |
97213
760.1 IPS |
|
Style Transfer (SP)
|
100% |
18539
23.8 IPS |
|
Style Transfer (HP)
|
100% |
162183
208.5 IPS |
|
Style Transfer (Q)
|
96% |
169707
219.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
4157
153.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
31060
1.15 KIPS |
|
Image Super-Resolution (Q)
|
99% |
35379
1.31 KIPS |
|
Text Classification (SP)
|
100% |
2564
3.42 KIPS |
|
Text Classification (HP)
|
100% |
2621
3.50 KIPS |
|
Text Classification (Q)
|
93% |
2445
3.28 KIPS |
|
Machine Translation (SP)
|
100% |
3435
59.2 IPS |
|
Machine Translation (HP)
|
100% |
5667
97.6 IPS |
|
Machine Translation (Q)
|
98% |
6245
107.9 IPS |