Upload Date | September 17 2024 01:16 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% |
1417
263.5 IPS |
|
Image Classification (HP)
|
100% |
10356
1.93 KIPS |
|
Image Classification (Q)
|
97% |
12280
2.29 KIPS |
|
Image Segmentation (SP)
|
100% |
1447
23.5 IPS |
|
Image Segmentation (HP)
|
100% |
11917
193.2 IPS |
|
Image Segmentation (Q)
|
99% |
13883
225.0 IPS |
|
Pose Estimation (SP)
|
100% |
6948
8.11 IPS |
|
Pose Estimation (HP)
|
100% |
96279
112.3 IPS |
|
Pose Estimation (Q)
|
95% |
101447
118.9 IPS |
|
Object Detection (SP)
|
100% |
1585
125.7 IPS |
|
Object Detection (HP)
|
100% |
12944
1.03 KIPS |
|
Object Detection (Q)
|
91% |
14357
1.15 KIPS |
|
Face Detection (SP)
|
100% |
3149
37.4 IPS |
|
Face Detection (HP)
|
100% |
30079
357.4 IPS |
|
Face Detection (Q)
|
100% |
37880
450.1 IPS |
|
Depth Estimation (SP)
|
100% |
6298
48.5 IPS |
|
Depth Estimation (HP)
|
99% |
74258
572.1 IPS |
|
Depth Estimation (Q)
|
85% |
95048
743.1 IPS |
|
Style Transfer (SP)
|
100% |
18879
24.3 IPS |
|
Style Transfer (HP)
|
100% |
167199
214.9 IPS |
|
Style Transfer (Q)
|
96% |
170713
220.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
4218
155.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
31758
1.17 KIPS |
|
Image Super-Resolution (Q)
|
99% |
36829
1.36 KIPS |
|
Text Classification (SP)
|
100% |
2655
3.54 KIPS |
|
Text Classification (HP)
|
100% |
2458
3.28 KIPS |
|
Text Classification (Q)
|
93% |
2598
3.49 KIPS |
|
Machine Translation (SP)
|
100% |
3455
59.5 IPS |
|
Machine Translation (HP)
|
100% |
2381
41.0 IPS |
|
Machine Translation (Q)
|
98% |
2380
41.1 IPS |