Upload Date | December 22 2024 09:04 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% |
1390
258.5 IPS |
|
Image Classification (HP)
|
100% |
10449
1.94 KIPS |
|
Image Classification (Q)
|
97% |
12870
2.40 KIPS |
|
Image Segmentation (SP)
|
100% |
1428
23.2 IPS |
|
Image Segmentation (HP)
|
100% |
15065
244.2 IPS |
|
Image Segmentation (Q)
|
99% |
18202
295.1 IPS |
|
Pose Estimation (SP)
|
100% |
6938
8.10 IPS |
|
Pose Estimation (HP)
|
100% |
96200
112.2 IPS |
|
Pose Estimation (Q)
|
95% |
101907
119.4 IPS |
|
Object Detection (SP)
|
100% |
1581
125.4 IPS |
|
Object Detection (HP)
|
100% |
12862
1.02 KIPS |
|
Object Detection (Q)
|
91% |
14600
1.17 KIPS |
|
Face Detection (SP)
|
100% |
2885
34.3 IPS |
|
Face Detection (HP)
|
100% |
30276
359.7 IPS |
|
Face Detection (Q)
|
100% |
38912
462.4 IPS |
|
Depth Estimation (SP)
|
100% |
6205
47.8 IPS |
|
Depth Estimation (HP)
|
99% |
75149
579.0 IPS |
|
Depth Estimation (Q)
|
85% |
95337
745.4 IPS |
|
Style Transfer (SP)
|
100% |
18875
24.3 IPS |
|
Style Transfer (HP)
|
100% |
166195
213.6 IPS |
|
Style Transfer (Q)
|
96% |
172578
222.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
4205
155.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
32127
1.19 KIPS |
|
Image Super-Resolution (Q)
|
99% |
38576
1.42 KIPS |
|
Text Classification (SP)
|
100% |
2619
3.50 KIPS |
|
Text Classification (HP)
|
100% |
2343
3.13 KIPS |
|
Text Classification (Q)
|
93% |
2491
3.34 KIPS |
|
Machine Translation (SP)
|
100% |
3447
59.4 IPS |
|
Machine Translation (HP)
|
100% |
7074
121.8 IPS |
|
Machine Translation (Q)
|
98% |
8076
139.6 IPS |