User | ESPD |
Upload Date | November 05 2024 03:35 AM |
Views | 5 |
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% |
1434
266.8 IPS |
|
Image Classification (HP)
|
100% |
10278
1.91 KIPS |
|
Image Classification (Q)
|
97% |
12706
2.37 KIPS |
|
Image Segmentation (SP)
|
100% |
1439
23.3 IPS |
|
Image Segmentation (HP)
|
100% |
14672
237.9 IPS |
|
Image Segmentation (Q)
|
99% |
18203
295.1 IPS |
|
Pose Estimation (SP)
|
100% |
6971
8.13 IPS |
|
Pose Estimation (HP)
|
100% |
98359
114.8 IPS |
|
Pose Estimation (Q)
|
95% |
103825
121.7 IPS |
|
Object Detection (SP)
|
100% |
1584
125.6 IPS |
|
Object Detection (HP)
|
100% |
12973
1.03 KIPS |
|
Object Detection (Q)
|
91% |
14708
1.18 KIPS |
|
Face Detection (SP)
|
100% |
3037
36.1 IPS |
|
Face Detection (HP)
|
100% |
30607
363.7 IPS |
|
Face Detection (Q)
|
100% |
39502
469.4 IPS |
|
Depth Estimation (SP)
|
100% |
6344
48.9 IPS |
|
Depth Estimation (HP)
|
99% |
75838
584.3 IPS |
|
Depth Estimation (Q)
|
85% |
97244
760.3 IPS |
|
Style Transfer (SP)
|
100% |
18915
24.3 IPS |
|
Style Transfer (HP)
|
100% |
163616
210.3 IPS |
|
Style Transfer (Q)
|
96% |
170797
220.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
4285
158.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
31486
1.16 KIPS |
|
Image Super-Resolution (Q)
|
99% |
36859
1.36 KIPS |
|
Text Classification (SP)
|
100% |
2639
3.52 KIPS |
|
Text Classification (HP)
|
100% |
2227
2.97 KIPS |
|
Text Classification (Q)
|
93% |
2627
3.53 KIPS |
|
Machine Translation (SP)
|
100% |
3420
58.9 IPS |
|
Machine Translation (HP)
|
100% |
5706
98.3 IPS |
|
Machine Translation (Q)
|
98% |
6096
105.3 IPS |