Upload Date | November 19 2024 01:31 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.2 |
Model | iPhone 14 Pro Max |
Model ID | iPhone15,3 |
Motherboard | D74AP |
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 | 5.51 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1423
264.7 IPS |
|
Image Classification (HP)
|
100% |
10109
1.88 KIPS |
|
Image Classification (Q)
|
97% |
12199
2.28 KIPS |
|
Image Segmentation (SP)
|
100% |
1423
23.1 IPS |
|
Image Segmentation (HP)
|
100% |
13420
217.5 IPS |
|
Image Segmentation (Q)
|
99% |
17908
290.3 IPS |
|
Pose Estimation (SP)
|
100% |
6797
7.93 IPS |
|
Pose Estimation (HP)
|
100% |
95248
111.1 IPS |
|
Pose Estimation (Q)
|
95% |
102218
119.8 IPS |
|
Object Detection (SP)
|
100% |
1585
125.8 IPS |
|
Object Detection (HP)
|
100% |
12876
1.02 KIPS |
|
Object Detection (Q)
|
91% |
14822
1.18 KIPS |
|
Face Detection (SP)
|
100% |
3072
36.5 IPS |
|
Face Detection (HP)
|
100% |
29541
351.0 IPS |
|
Face Detection (Q)
|
100% |
39212
465.9 IPS |
|
Depth Estimation (SP)
|
100% |
6054
46.6 IPS |
|
Depth Estimation (HP)
|
99% |
75065
578.3 IPS |
|
Depth Estimation (Q)
|
85% |
95259
744.8 IPS |
|
Style Transfer (SP)
|
100% |
18742
24.1 IPS |
|
Style Transfer (HP)
|
100% |
168276
216.3 IPS |
|
Style Transfer (Q)
|
96% |
167211
215.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
4158
153.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
34142
1.26 KIPS |
|
Image Super-Resolution (Q)
|
99% |
37013
1.37 KIPS |
|
Text Classification (SP)
|
100% |
2623
3.50 KIPS |
|
Text Classification (HP)
|
100% |
2126
2.84 KIPS |
|
Text Classification (Q)
|
93% |
1838
2.47 KIPS |
|
Machine Translation (SP)
|
100% |
3451
59.4 IPS |
|
Machine Translation (HP)
|
100% |
7084
122.0 IPS |
|
Machine Translation (Q)
|
98% |
7930
137.0 IPS |