Upload Date | September 18 2024 04:33 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.0 |
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% |
1425
265.0 IPS |
|
Image Classification (HP)
|
100% |
10008
1.86 KIPS |
|
Image Classification (Q)
|
97% |
13201
2.46 KIPS |
|
Image Segmentation (SP)
|
100% |
1432
23.2 IPS |
|
Image Segmentation (HP)
|
100% |
11532
186.9 IPS |
|
Image Segmentation (Q)
|
99% |
13060
211.7 IPS |
|
Pose Estimation (SP)
|
100% |
7165
8.36 IPS |
|
Pose Estimation (HP)
|
100% |
95555
111.5 IPS |
|
Pose Estimation (Q)
|
95% |
101002
118.4 IPS |
|
Object Detection (SP)
|
100% |
1579
125.2 IPS |
|
Object Detection (HP)
|
100% |
12892
1.02 KIPS |
|
Object Detection (Q)
|
91% |
14592
1.17 KIPS |
|
Face Detection (SP)
|
100% |
3002
35.7 IPS |
|
Face Detection (HP)
|
100% |
29916
355.5 IPS |
|
Face Detection (Q)
|
100% |
37608
446.9 IPS |
|
Depth Estimation (SP)
|
100% |
6240
48.1 IPS |
|
Depth Estimation (HP)
|
99% |
75968
585.3 IPS |
|
Depth Estimation (Q)
|
85% |
95213
744.4 IPS |
|
Style Transfer (SP)
|
100% |
18904
24.3 IPS |
|
Style Transfer (HP)
|
100% |
165734
213.1 IPS |
|
Style Transfer (Q)
|
96% |
167004
215.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
4220
155.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
31281
1.16 KIPS |
|
Image Super-Resolution (Q)
|
99% |
36390
1.34 KIPS |
|
Text Classification (SP)
|
100% |
2627
3.51 KIPS |
|
Text Classification (HP)
|
100% |
2417
3.23 KIPS |
|
Text Classification (Q)
|
93% |
2125
2.85 KIPS |
|
Machine Translation (SP)
|
100% |
3408
58.7 IPS |
|
Machine Translation (HP)
|
100% |
2380
41.0 IPS |
|
Machine Translation (Q)
|
98% |
2423
41.9 IPS |