User | M91 |
Upload Date | September 30 2024 11:16 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.1 |
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% |
1439
267.5 IPS |
|
Image Classification (HP)
|
100% |
9553
1.78 KIPS |
|
Image Classification (Q)
|
97% |
11772
2.20 KIPS |
|
Image Segmentation (SP)
|
100% |
1434
23.3 IPS |
|
Image Segmentation (HP)
|
100% |
14470
234.6 IPS |
|
Image Segmentation (Q)
|
99% |
17729
287.4 IPS |
|
Pose Estimation (SP)
|
100% |
6942
8.10 IPS |
|
Pose Estimation (HP)
|
100% |
95306
111.2 IPS |
|
Pose Estimation (Q)
|
95% |
101112
118.5 IPS |
|
Object Detection (SP)
|
100% |
1578
125.2 IPS |
|
Object Detection (HP)
|
100% |
12805
1.02 KIPS |
|
Object Detection (Q)
|
91% |
14671
1.17 KIPS |
|
Face Detection (SP)
|
100% |
3058
36.3 IPS |
|
Face Detection (HP)
|
100% |
30088
357.5 IPS |
|
Face Detection (Q)
|
100% |
37988
451.4 IPS |
|
Depth Estimation (SP)
|
100% |
6192
47.7 IPS |
|
Depth Estimation (HP)
|
99% |
74643
575.1 IPS |
|
Depth Estimation (Q)
|
85% |
95330
745.3 IPS |
|
Style Transfer (SP)
|
100% |
18937
24.3 IPS |
|
Style Transfer (HP)
|
100% |
165291
212.5 IPS |
|
Style Transfer (Q)
|
96% |
166512
214.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
4169
153.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
32506
1.20 KIPS |
|
Image Super-Resolution (Q)
|
99% |
37223
1.37 KIPS |
|
Text Classification (SP)
|
100% |
2645
3.53 KIPS |
|
Text Classification (HP)
|
100% |
2057
2.75 KIPS |
|
Text Classification (Q)
|
93% |
2032
2.73 KIPS |
|
Machine Translation (SP)
|
100% |
3450
59.4 IPS |
|
Machine Translation (HP)
|
100% |
2348
40.4 IPS |
|
Machine Translation (Q)
|
98% |
2358
40.8 IPS |