Upload Date | September 18 2024 01:17 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.0 |
Model | iPhone 14 Pro |
Model ID | iPhone15,2 |
Motherboard | D73AP |
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 | 5.53 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1437
267.2 IPS |
|
Image Classification (HP)
|
100% |
10363
1.93 KIPS |
|
Image Classification (Q)
|
97% |
11901
2.22 KIPS |
|
Image Segmentation (SP)
|
100% |
1453
23.5 IPS |
|
Image Segmentation (HP)
|
100% |
11267
182.7 IPS |
|
Image Segmentation (Q)
|
99% |
14054
227.8 IPS |
|
Pose Estimation (SP)
|
100% |
7149
8.34 IPS |
|
Pose Estimation (HP)
|
100% |
100528
117.3 IPS |
|
Pose Estimation (Q)
|
95% |
101680
119.2 IPS |
|
Object Detection (SP)
|
100% |
1583
125.6 IPS |
|
Object Detection (HP)
|
100% |
12872
1.02 KIPS |
|
Object Detection (Q)
|
91% |
14853
1.19 KIPS |
|
Face Detection (SP)
|
100% |
2991
35.5 IPS |
|
Face Detection (HP)
|
100% |
29521
350.8 IPS |
|
Face Detection (Q)
|
100% |
37519
445.8 IPS |
|
Depth Estimation (SP)
|
100% |
6222
47.9 IPS |
|
Depth Estimation (HP)
|
99% |
75512
581.8 IPS |
|
Depth Estimation (Q)
|
85% |
95467
746.4 IPS |
|
Style Transfer (SP)
|
100% |
19251
24.7 IPS |
|
Style Transfer (HP)
|
100% |
169982
218.5 IPS |
|
Style Transfer (Q)
|
96% |
174642
225.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
4340
160.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
33612
1.24 KIPS |
|
Image Super-Resolution (Q)
|
99% |
36911
1.36 KIPS |
|
Text Classification (SP)
|
100% |
2628
3.51 KIPS |
|
Text Classification (HP)
|
100% |
1916
2.56 KIPS |
|
Text Classification (Q)
|
93% |
2086
2.80 KIPS |
|
Machine Translation (SP)
|
100% |
3441
59.3 IPS |
|
Machine Translation (HP)
|
100% |
2411
41.5 IPS |
|
Machine Translation (Q)
|
98% |
2372
41.0 IPS |