Upload Date | September 18 2024 12:50 PM |
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% |
1400
260.4 IPS |
|
Image Classification (HP)
|
100% |
10532
1.96 KIPS |
|
Image Classification (Q)
|
97% |
12913
2.41 KIPS |
|
Image Segmentation (SP)
|
100% |
1455
23.6 IPS |
|
Image Segmentation (HP)
|
100% |
11478
186.1 IPS |
|
Image Segmentation (Q)
|
99% |
13508
219.0 IPS |
|
Pose Estimation (SP)
|
100% |
7112
8.30 IPS |
|
Pose Estimation (HP)
|
100% |
97678
114.0 IPS |
|
Pose Estimation (Q)
|
95% |
102728
120.4 IPS |
|
Object Detection (SP)
|
100% |
1578
125.1 IPS |
|
Object Detection (HP)
|
100% |
13064
1.04 KIPS |
|
Object Detection (Q)
|
91% |
14682
1.17 KIPS |
|
Face Detection (SP)
|
100% |
3089
36.7 IPS |
|
Face Detection (HP)
|
100% |
30026
356.8 IPS |
|
Face Detection (Q)
|
100% |
38951
462.8 IPS |
|
Depth Estimation (SP)
|
100% |
6351
48.9 IPS |
|
Depth Estimation (HP)
|
99% |
75900
584.8 IPS |
|
Depth Estimation (Q)
|
85% |
95718
748.4 IPS |
|
Style Transfer (SP)
|
100% |
19132
24.6 IPS |
|
Style Transfer (HP)
|
100% |
169400
217.8 IPS |
|
Style Transfer (Q)
|
96% |
172000
222.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
4256
157.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
31917
1.18 KIPS |
|
Image Super-Resolution (Q)
|
99% |
37291
1.38 KIPS |
|
Text Classification (SP)
|
100% |
2620
3.50 KIPS |
|
Text Classification (HP)
|
100% |
2487
3.32 KIPS |
|
Text Classification (Q)
|
93% |
2044
2.74 KIPS |
|
Machine Translation (SP)
|
100% |
3437
59.2 IPS |
|
Machine Translation (HP)
|
100% |
2396
41.3 IPS |
|
Machine Translation (Q)
|
98% |
2397
41.4 IPS |