Upload Date | September 19 2024 12:50 AM |
Views | 2 |
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% |
1411
262.5 IPS |
|
Image Classification (HP)
|
100% |
10440
1.94 KIPS |
|
Image Classification (Q)
|
97% |
12683
2.37 KIPS |
|
Image Segmentation (SP)
|
100% |
1440
23.3 IPS |
|
Image Segmentation (HP)
|
100% |
11698
189.6 IPS |
|
Image Segmentation (Q)
|
99% |
13133
212.9 IPS |
|
Pose Estimation (SP)
|
100% |
6662
7.77 IPS |
|
Pose Estimation (HP)
|
100% |
99056
115.6 IPS |
|
Pose Estimation (Q)
|
95% |
101329
118.8 IPS |
|
Object Detection (SP)
|
100% |
1572
124.7 IPS |
|
Object Detection (HP)
|
100% |
13041
1.03 KIPS |
|
Object Detection (Q)
|
91% |
15115
1.21 KIPS |
|
Face Detection (SP)
|
100% |
3131
37.2 IPS |
|
Face Detection (HP)
|
100% |
30900
367.2 IPS |
|
Face Detection (Q)
|
100% |
38987
463.2 IPS |
|
Depth Estimation (SP)
|
100% |
6174
47.6 IPS |
|
Depth Estimation (HP)
|
99% |
75690
583.1 IPS |
|
Depth Estimation (Q)
|
85% |
96557
754.9 IPS |
|
Style Transfer (SP)
|
100% |
18719
24.1 IPS |
|
Style Transfer (HP)
|
100% |
163547
210.2 IPS |
|
Style Transfer (Q)
|
96% |
173645
224.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
4119
152.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
33729
1.25 KIPS |
|
Image Super-Resolution (Q)
|
99% |
37448
1.38 KIPS |
|
Text Classification (SP)
|
100% |
2605
3.48 KIPS |
|
Text Classification (HP)
|
100% |
2339
3.12 KIPS |
|
Text Classification (Q)
|
93% |
2241
3.01 KIPS |
|
Machine Translation (SP)
|
100% |
3445
59.3 IPS |
|
Machine Translation (HP)
|
100% |
2382
41.0 IPS |
|
Machine Translation (Q)
|
98% |
2424
41.9 IPS |