User | crisss1205 |
Upload Date | August 15 2024 11:02 PM |
Views | 8 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.1 |
Model | iPhone 15 Pro Max |
Model ID | iPhone16,2 |
Motherboard | D84AP |
CPU Information | |
---|---|
Name | Apple A17 Pro |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.78 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.48 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
581
108.0 IPS |
|
Image Classification (HP)
|
100% |
7139
1.33 KIPS |
|
Image Classification (Q)
|
99% |
6910
1.29 KIPS |
|
Image Segmentation (SP)
|
100% |
757
12.3 IPS |
|
Image Segmentation (HP)
|
100% |
6973
113.0 IPS |
|
Image Segmentation (Q)
|
100% |
7062
114.5 IPS |
|
Pose Estimation (SP)
|
100% |
1916
2.24 IPS |
|
Pose Estimation (HP)
|
100% |
34059
39.7 IPS |
|
Pose Estimation (Q)
|
94% |
66807
78.4 IPS |
|
Object Detection (SP)
|
100% |
429
34.0 IPS |
|
Object Detection (HP)
|
100% |
5411
429.2 IPS |
|
Object Detection (Q)
|
91% |
9732
777.6 IPS |
|
Face Detection (SP)
|
100% |
875
10.4 IPS |
|
Face Detection (HP)
|
100% |
13371
158.9 IPS |
|
Face Detection (Q)
|
100% |
20142
239.3 IPS |
|
Depth Estimation (SP)
|
100% |
2693
20.7 IPS |
|
Depth Estimation (HP)
|
99% |
35918
276.7 IPS |
|
Depth Estimation (Q)
|
97% |
36892
285.3 IPS |
|
Style Transfer (SP)
|
100% |
4969
6.39 IPS |
|
Style Transfer (HP)
|
100% |
67014
86.1 IPS |
|
Style Transfer (Q)
|
100% |
71361
91.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
1058
39.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
18655
688.9 IPS |
|
Image Super-Resolution (Q)
|
98% |
28181
1.04 KIPS |
|
Text Classification (SP)
|
100% |
1329
1.77 KIPS |
|
Text Classification (HP)
|
100% |
1674
2.23 KIPS |
|
Text Classification (Q)
|
93% |
1820
2.44 KIPS |
|
Machine Translation (SP)
|
100% |
1436
24.7 IPS |
|
Machine Translation (HP)
|
100% |
4280
73.7 IPS |
|
Machine Translation (Q)
|
98% |
5025
86.8 IPS |