User | M91 |
Upload Date | October 15 2024 10:48 AM |
Views | 4 |
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% |
1413
262.7 IPS |
|
Image Classification (HP)
|
100% |
10301
1.92 KIPS |
|
Image Classification (Q)
|
97% |
12607
2.35 KIPS |
|
Image Segmentation (SP)
|
100% |
1431
23.2 IPS |
|
Image Segmentation (HP)
|
100% |
13721
222.4 IPS |
|
Image Segmentation (Q)
|
99% |
17900
290.2 IPS |
|
Pose Estimation (SP)
|
100% |
6727
7.85 IPS |
|
Pose Estimation (HP)
|
100% |
95423
111.3 IPS |
|
Pose Estimation (Q)
|
95% |
103363
121.1 IPS |
|
Object Detection (SP)
|
100% |
1568
124.4 IPS |
|
Object Detection (HP)
|
100% |
12797
1.02 KIPS |
|
Object Detection (Q)
|
91% |
15074
1.20 KIPS |
|
Face Detection (SP)
|
100% |
2970
35.3 IPS |
|
Face Detection (HP)
|
100% |
30608
363.7 IPS |
|
Face Detection (Q)
|
100% |
39355
467.6 IPS |
|
Depth Estimation (SP)
|
100% |
6325
48.7 IPS |
|
Depth Estimation (HP)
|
99% |
74704
575.6 IPS |
|
Depth Estimation (Q)
|
85% |
97890
765.4 IPS |
|
Style Transfer (SP)
|
100% |
18644
24.0 IPS |
|
Style Transfer (HP)
|
100% |
163346
210.0 IPS |
|
Style Transfer (Q)
|
96% |
167983
216.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
4189
154.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
31480
1.16 KIPS |
|
Image Super-Resolution (Q)
|
99% |
36353
1.34 KIPS |
|
Text Classification (SP)
|
100% |
2673
3.57 KIPS |
|
Text Classification (HP)
|
100% |
2442
3.26 KIPS |
|
Text Classification (Q)
|
93% |
2667
3.58 KIPS |
|
Machine Translation (SP)
|
100% |
3441
59.3 IPS |
|
Machine Translation (HP)
|
100% |
5606
96.6 IPS |
|
Machine Translation (Q)
|
98% |
6180
106.8 IPS |