User | kirbalo |
Upload Date | August 15 2024 05:43 PM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 17.6.1 |
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 | 5.50 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1235
229.7 IPS |
|
Image Classification (HP)
|
100% |
5775
1.07 KIPS |
|
Image Classification (Q)
|
99% |
6041
1.13 KIPS |
|
Image Segmentation (SP)
|
100% |
745
12.1 IPS |
|
Image Segmentation (HP)
|
100% |
5082
82.4 IPS |
|
Image Segmentation (Q)
|
100% |
5134
83.2 IPS |
|
Pose Estimation (SP)
|
100% |
6383
7.45 IPS |
|
Pose Estimation (HP)
|
100% |
80953
94.5 IPS |
|
Pose Estimation (Q)
|
94% |
85273
100.0 IPS |
|
Object Detection (SP)
|
100% |
1324
105.0 IPS |
|
Object Detection (HP)
|
100% |
7210
571.9 IPS |
|
Object Detection (Q)
|
93% |
8401
670.3 IPS |
|
Face Detection (SP)
|
100% |
2141
25.4 IPS |
|
Face Detection (HP)
|
100% |
10788
128.2 IPS |
|
Face Detection (Q)
|
100% |
12522
148.8 IPS |
|
Depth Estimation (SP)
|
100% |
4150
32.0 IPS |
|
Depth Estimation (HP)
|
99% |
44514
343.0 IPS |
|
Depth Estimation (Q)
|
97% |
45455
351.5 IPS |
|
Style Transfer (SP)
|
100% |
11241
14.4 IPS |
|
Style Transfer (HP)
|
100% |
121663
156.4 IPS |
|
Style Transfer (Q)
|
100% |
122183
157.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
3269
120.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
16232
599.4 IPS |
|
Image Super-Resolution (Q)
|
98% |
21418
793.5 IPS |
|
Text Classification (SP)
|
100% |
1387
1.85 KIPS |
|
Text Classification (HP)
|
100% |
3574
4.77 KIPS |
|
Text Classification (Q)
|
93% |
3281
4.40 KIPS |
|
Machine Translation (SP)
|
100% |
1666
28.7 IPS |
|
Machine Translation (HP)
|
100% |
2381
41.0 IPS |
|
Machine Translation (Q)
|
98% |
2343
40.5 IPS |