Upload Date | September 17 2024 12:24 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A15 Bionic |
System Information | |
---|---|
Operating System | iOS 18.0 |
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% |
1330
247.3 IPS |
|
Image Classification (HP)
|
100% |
9400
1.75 KIPS |
|
Image Classification (Q)
|
96% |
9682
1.81 KIPS |
|
Image Segmentation (SP)
|
100% |
1293
21.0 IPS |
|
Image Segmentation (HP)
|
100% |
6882
111.6 IPS |
|
Image Segmentation (Q)
|
99% |
7463
121.0 IPS |
|
Pose Estimation (SP)
|
100% |
6369
7.43 IPS |
|
Pose Estimation (HP)
|
100% |
87531
102.1 IPS |
|
Pose Estimation (Q)
|
95% |
93692
109.8 IPS |
|
Object Detection (SP)
|
100% |
1424
112.9 IPS |
|
Object Detection (HP)
|
99% |
10660
848.0 IPS |
|
Object Detection (Q)
|
91% |
11124
888.9 IPS |
|
Face Detection (SP)
|
100% |
2674
31.8 IPS |
|
Face Detection (HP)
|
100% |
25264
300.2 IPS |
|
Face Detection (Q)
|
100% |
31210
370.8 IPS |
|
Depth Estimation (SP)
|
100% |
5442
41.9 IPS |
|
Depth Estimation (HP)
|
99% |
55289
426.0 IPS |
|
Depth Estimation (Q)
|
85% |
74020
578.4 IPS |
|
Style Transfer (SP)
|
100% |
17404
22.4 IPS |
|
Style Transfer (HP)
|
100% |
156758
201.5 IPS |
|
Style Transfer (Q)
|
96% |
153729
198.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
3874
143.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
25884
955.8 IPS |
|
Image Super-Resolution (Q)
|
99% |
28429
1.05 KIPS |
|
Text Classification (SP)
|
100% |
2416
3.22 KIPS |
|
Text Classification (HP)
|
100% |
2341
3.13 KIPS |
|
Text Classification (Q)
|
93% |
2362
3.17 KIPS |
|
Machine Translation (SP)
|
100% |
3406
58.7 IPS |
|
Machine Translation (HP)
|
100% |
2246
38.7 IPS |
|
Machine Translation (Q)
|
98% |
2236
38.6 IPS |