Upload Date | December 27 2024 06:52 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.2 |
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% |
1430
265.9 IPS |
|
Image Classification (HP)
|
100% |
10519
1.96 KIPS |
|
Image Classification (Q)
|
97% |
12160
2.27 KIPS |
|
Image Segmentation (SP)
|
100% |
1428
23.1 IPS |
|
Image Segmentation (HP)
|
100% |
13396
217.2 IPS |
|
Image Segmentation (Q)
|
99% |
17881
289.9 IPS |
|
Pose Estimation (SP)
|
100% |
7016
8.19 IPS |
|
Pose Estimation (HP)
|
100% |
98891
115.4 IPS |
|
Pose Estimation (Q)
|
95% |
102888
120.6 IPS |
|
Object Detection (SP)
|
100% |
1569
124.5 IPS |
|
Object Detection (HP)
|
100% |
12930
1.03 KIPS |
|
Object Detection (Q)
|
91% |
14865
1.19 KIPS |
|
Face Detection (SP)
|
100% |
3024
35.9 IPS |
|
Face Detection (HP)
|
100% |
29992
356.4 IPS |
|
Face Detection (Q)
|
100% |
38812
461.2 IPS |
|
Depth Estimation (SP)
|
100% |
6187
47.7 IPS |
|
Depth Estimation (HP)
|
99% |
74714
575.6 IPS |
|
Depth Estimation (Q)
|
85% |
94940
742.3 IPS |
|
Style Transfer (SP)
|
100% |
18720
24.1 IPS |
|
Style Transfer (HP)
|
100% |
163720
210.5 IPS |
|
Style Transfer (Q)
|
96% |
169037
218.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
4220
155.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
31914
1.18 KIPS |
|
Image Super-Resolution (Q)
|
99% |
36488
1.35 KIPS |
|
Text Classification (SP)
|
100% |
2651
3.54 KIPS |
|
Text Classification (HP)
|
100% |
2501
3.34 KIPS |
|
Text Classification (Q)
|
93% |
2191
2.94 KIPS |
|
Machine Translation (SP)
|
100% |
3425
59.0 IPS |
|
Machine Translation (HP)
|
100% |
7079
121.9 IPS |
|
Machine Translation (Q)
|
98% |
7618
131.6 IPS |