Upload Date | November 20 2024 10:01 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A15 Bionic |
System Information | |
---|---|
Operating System | iOS 18.1.1 |
Model | iPhone 13 Pro Max |
Model ID | iPhone14,3 |
Motherboard | D64AP |
CPU Information | |
---|---|
Name | Apple A15 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.23 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 5.51 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1341
249.3 IPS |
|
Image Classification (HP)
|
100% |
8055
1.50 KIPS |
|
Image Classification (Q)
|
96% |
10122
1.89 KIPS |
|
Image Segmentation (SP)
|
100% |
1085
17.6 IPS |
|
Image Segmentation (HP)
|
100% |
11601
188.1 IPS |
|
Image Segmentation (Q)
|
99% |
14581
236.4 IPS |
|
Pose Estimation (SP)
|
100% |
5967
6.96 IPS |
|
Pose Estimation (HP)
|
100% |
88449
103.2 IPS |
|
Pose Estimation (Q)
|
95% |
93133
109.2 IPS |
|
Object Detection (SP)
|
100% |
1417
112.4 IPS |
|
Object Detection (HP)
|
99% |
10470
832.8 IPS |
|
Object Detection (Q)
|
91% |
11338
906.0 IPS |
|
Face Detection (SP)
|
100% |
2542
30.2 IPS |
|
Face Detection (HP)
|
100% |
28392
337.4 IPS |
|
Face Detection (Q)
|
100% |
35481
421.6 IPS |
|
Depth Estimation (SP)
|
100% |
4853
37.4 IPS |
|
Depth Estimation (HP)
|
99% |
54597
420.6 IPS |
|
Depth Estimation (Q)
|
85% |
73024
570.7 IPS |
|
Style Transfer (SP)
|
100% |
17127
22.0 IPS |
|
Style Transfer (HP)
|
100% |
161116
207.1 IPS |
|
Style Transfer (Q)
|
96% |
161701
208.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
3947
145.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
28470
1.05 KIPS |
|
Image Super-Resolution (Q)
|
99% |
30862
1.14 KIPS |
|
Text Classification (SP)
|
100% |
2474
3.30 KIPS |
|
Text Classification (HP)
|
100% |
2435
3.25 KIPS |
|
Text Classification (Q)
|
93% |
2436
3.27 KIPS |
|
Machine Translation (SP)
|
100% |
3261
56.2 IPS |
|
Machine Translation (HP)
|
100% |
4882
84.1 IPS |
|
Machine Translation (Q)
|
98% |
5297
91.5 IPS |