Upload Date | September 18 2024 07:04 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A15 Bionic |
System Information | |
---|---|
Operating System | iOS 18.0 |
Model | iPhone 14 Plus |
Model ID | iPhone14,8 |
Motherboard | D28AP |
CPU Information | |
---|---|
Name | Apple A15 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.23 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 5.55 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1359
252.8 IPS |
|
Image Classification (HP)
|
100% |
8727
1.62 KIPS |
|
Image Classification (Q)
|
96% |
10315
1.93 KIPS |
|
Image Segmentation (SP)
|
100% |
1355
22.0 IPS |
|
Image Segmentation (HP)
|
100% |
7170
116.2 IPS |
|
Image Segmentation (Q)
|
99% |
7604
123.3 IPS |
|
Pose Estimation (SP)
|
100% |
6367
7.43 IPS |
|
Pose Estimation (HP)
|
100% |
85619
99.9 IPS |
|
Pose Estimation (Q)
|
95% |
93126
109.1 IPS |
|
Object Detection (SP)
|
100% |
1450
115.0 IPS |
|
Object Detection (HP)
|
99% |
10640
846.4 IPS |
|
Object Detection (Q)
|
91% |
11015
880.1 IPS |
|
Face Detection (SP)
|
100% |
2828
33.6 IPS |
|
Face Detection (HP)
|
100% |
25725
305.7 IPS |
|
Face Detection (Q)
|
100% |
34099
405.2 IPS |
|
Depth Estimation (SP)
|
100% |
5497
42.4 IPS |
|
Depth Estimation (HP)
|
99% |
53436
411.7 IPS |
|
Depth Estimation (Q)
|
85% |
70454
550.6 IPS |
|
Style Transfer (SP)
|
100% |
17319
22.3 IPS |
|
Style Transfer (HP)
|
100% |
154501
198.6 IPS |
|
Style Transfer (Q)
|
96% |
151039
194.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
3865
142.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
25931
957.5 IPS |
|
Image Super-Resolution (Q)
|
99% |
28039
1.04 KIPS |
|
Text Classification (SP)
|
100% |
2421
3.23 KIPS |
|
Text Classification (HP)
|
100% |
2303
3.07 KIPS |
|
Text Classification (Q)
|
93% |
2102
2.82 KIPS |
|
Machine Translation (SP)
|
100% |
3491
60.1 IPS |
|
Machine Translation (HP)
|
100% |
2204
38.0 IPS |
|
Machine Translation (Q)
|
98% |
2187
37.8 IPS |