User | SRLMJ23 |
Upload Date | September 26 2024 05:19 AM |
Views | 3 |
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% |
1438
267.5 IPS |
|
Image Classification (HP)
|
100% |
10211
1.90 KIPS |
|
Image Classification (Q)
|
97% |
12503
2.33 KIPS |
|
Image Segmentation (SP)
|
100% |
1435
23.3 IPS |
|
Image Segmentation (HP)
|
100% |
12187
197.6 IPS |
|
Image Segmentation (Q)
|
99% |
13613
220.7 IPS |
|
Pose Estimation (SP)
|
100% |
6925
8.08 IPS |
|
Pose Estimation (HP)
|
100% |
98659
115.1 IPS |
|
Pose Estimation (Q)
|
95% |
102145
119.7 IPS |
|
Object Detection (SP)
|
100% |
1575
125.0 IPS |
|
Object Detection (HP)
|
100% |
12393
983.0 IPS |
|
Object Detection (Q)
|
91% |
14396
1.15 KIPS |
|
Face Detection (SP)
|
100% |
3087
36.7 IPS |
|
Face Detection (HP)
|
100% |
29795
354.0 IPS |
|
Face Detection (Q)
|
100% |
37945
450.9 IPS |
|
Depth Estimation (SP)
|
100% |
6232
48.0 IPS |
|
Depth Estimation (HP)
|
99% |
74777
576.1 IPS |
|
Depth Estimation (Q)
|
85% |
96747
756.4 IPS |
|
Style Transfer (SP)
|
100% |
18829
24.2 IPS |
|
Style Transfer (HP)
|
100% |
165689
213.0 IPS |
|
Style Transfer (Q)
|
96% |
168615
217.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
4240
156.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
30970
1.14 KIPS |
|
Image Super-Resolution (Q)
|
99% |
35767
1.32 KIPS |
|
Text Classification (SP)
|
100% |
2588
3.45 KIPS |
|
Text Classification (HP)
|
100% |
2306
3.08 KIPS |
|
Text Classification (Q)
|
93% |
2321
3.12 KIPS |
|
Machine Translation (SP)
|
100% |
3425
59.0 IPS |
|
Machine Translation (HP)
|
100% |
2409
41.5 IPS |
|
Machine Translation (Q)
|
98% |
2419
41.8 IPS |