Upload Date | September 17 2024 03:47 PM |
Views | 2 |
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% |
1441
268.1 IPS |
|
Image Classification (HP)
|
100% |
10339
1.92 KIPS |
|
Image Classification (Q)
|
97% |
13112
2.45 KIPS |
|
Image Segmentation (SP)
|
100% |
1443
23.4 IPS |
|
Image Segmentation (HP)
|
100% |
11579
187.7 IPS |
|
Image Segmentation (Q)
|
99% |
13239
214.6 IPS |
|
Pose Estimation (SP)
|
100% |
7060
8.24 IPS |
|
Pose Estimation (HP)
|
100% |
97131
113.3 IPS |
|
Pose Estimation (Q)
|
95% |
102862
120.6 IPS |
|
Object Detection (SP)
|
100% |
1587
125.9 IPS |
|
Object Detection (HP)
|
100% |
12903
1.02 KIPS |
|
Object Detection (Q)
|
91% |
14624
1.17 KIPS |
|
Face Detection (SP)
|
100% |
3141
37.3 IPS |
|
Face Detection (HP)
|
100% |
30120
357.9 IPS |
|
Face Detection (Q)
|
100% |
39314
467.1 IPS |
|
Depth Estimation (SP)
|
100% |
6257
48.2 IPS |
|
Depth Estimation (HP)
|
99% |
75661
582.9 IPS |
|
Depth Estimation (Q)
|
85% |
96131
751.6 IPS |
|
Style Transfer (SP)
|
100% |
19032
24.5 IPS |
|
Style Transfer (HP)
|
100% |
171755
220.8 IPS |
|
Style Transfer (Q)
|
96% |
172690
222.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
4327
159.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
32637
1.21 KIPS |
|
Image Super-Resolution (Q)
|
99% |
37690
1.39 KIPS |
|
Text Classification (SP)
|
100% |
2641
3.53 KIPS |
|
Text Classification (HP)
|
100% |
2610
3.48 KIPS |
|
Text Classification (Q)
|
93% |
2213
2.97 KIPS |
|
Machine Translation (SP)
|
100% |
3466
59.7 IPS |
|
Machine Translation (HP)
|
100% |
2384
41.1 IPS |
|
Machine Translation (Q)
|
98% |
2371
41.0 IPS |