Upload Date | September 16 2024 10:24 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 17.7 |
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 | 5.48 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1220
226.8 IPS |
|
Image Classification (HP)
|
100% |
5879
1.09 KIPS |
|
Image Classification (Q)
|
97% |
6341
1.18 KIPS |
|
Image Segmentation (SP)
|
100% |
742
12.0 IPS |
|
Image Segmentation (HP)
|
100% |
5110
82.8 IPS |
|
Image Segmentation (Q)
|
99% |
9515
154.2 IPS |
|
Pose Estimation (SP)
|
100% |
6246
7.29 IPS |
|
Pose Estimation (HP)
|
100% |
78235
91.3 IPS |
|
Pose Estimation (Q)
|
95% |
85750
100.5 IPS |
|
Object Detection (SP)
|
100% |
1323
104.9 IPS |
|
Object Detection (HP)
|
100% |
7692
610.1 IPS |
|
Object Detection (Q)
|
93% |
8293
661.7 IPS |
|
Face Detection (SP)
|
100% |
2157
25.6 IPS |
|
Face Detection (HP)
|
100% |
10525
125.1 IPS |
|
Face Detection (Q)
|
100% |
13065
155.2 IPS |
|
Depth Estimation (SP)
|
100% |
3897
30.0 IPS |
|
Depth Estimation (HP)
|
99% |
44083
339.6 IPS |
|
Depth Estimation (Q)
|
85% |
50941
398.3 IPS |
|
Style Transfer (SP)
|
100% |
10432
13.4 IPS |
|
Style Transfer (HP)
|
100% |
119388
153.5 IPS |
|
Style Transfer (Q)
|
96% |
104607
135.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
2052
75.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
16740
618.1 IPS |
|
Image Super-Resolution (Q)
|
99% |
21617
798.2 IPS |
|
Text Classification (SP)
|
100% |
1043
1.39 KIPS |
|
Text Classification (HP)
|
100% |
2225
2.97 KIPS |
|
Text Classification (Q)
|
93% |
2756
3.70 KIPS |
|
Machine Translation (SP)
|
100% |
1453
25.0 IPS |
|
Machine Translation (HP)
|
100% |
2078
35.8 IPS |
|
Machine Translation (Q)
|
98% |
2242
38.7 IPS |