Upload Date | September 18 2024 10:52 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% |
1413
262.9 IPS |
|
Image Classification (HP)
|
100% |
10003
1.86 KIPS |
|
Image Classification (Q)
|
97% |
12665
2.36 KIPS |
|
Image Segmentation (SP)
|
100% |
1449
23.5 IPS |
|
Image Segmentation (HP)
|
100% |
12080
195.8 IPS |
|
Image Segmentation (Q)
|
99% |
13485
218.6 IPS |
|
Pose Estimation (SP)
|
100% |
7138
8.33 IPS |
|
Pose Estimation (HP)
|
100% |
96541
112.6 IPS |
|
Pose Estimation (Q)
|
95% |
102737
120.4 IPS |
|
Object Detection (SP)
|
100% |
1584
125.7 IPS |
|
Object Detection (HP)
|
100% |
13004
1.03 KIPS |
|
Object Detection (Q)
|
91% |
15159
1.21 KIPS |
|
Face Detection (SP)
|
100% |
3116
37.0 IPS |
|
Face Detection (HP)
|
100% |
30915
367.3 IPS |
|
Face Detection (Q)
|
100% |
38492
457.4 IPS |
|
Depth Estimation (SP)
|
100% |
6266
48.3 IPS |
|
Depth Estimation (HP)
|
99% |
74691
575.5 IPS |
|
Depth Estimation (Q)
|
85% |
96243
752.5 IPS |
|
Style Transfer (SP)
|
100% |
19031
24.5 IPS |
|
Style Transfer (HP)
|
100% |
168698
216.9 IPS |
|
Style Transfer (Q)
|
96% |
171835
221.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
4243
156.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
32025
1.18 KIPS |
|
Image Super-Resolution (Q)
|
99% |
36649
1.35 KIPS |
|
Text Classification (SP)
|
100% |
2609
3.48 KIPS |
|
Text Classification (HP)
|
100% |
2287
3.05 KIPS |
|
Text Classification (Q)
|
93% |
2327
3.12 KIPS |
|
Machine Translation (SP)
|
100% |
3457
59.6 IPS |
|
Machine Translation (HP)
|
100% |
2362
40.7 IPS |
|
Machine Translation (Q)
|
98% |
2359
40.8 IPS |