User | doremon0710 |
Upload Date | August 15 2024 08:07 PM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 17.6.1 |
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 | 7.44 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1435
266.9 IPS |
|
Image Classification (HP)
|
100% |
6209
1.15 KIPS |
|
Image Classification (Q)
|
99% |
7020
1.31 KIPS |
|
Image Segmentation (SP)
|
100% |
829
13.4 IPS |
|
Image Segmentation (HP)
|
100% |
5204
84.4 IPS |
|
Image Segmentation (Q)
|
100% |
5389
87.4 IPS |
|
Pose Estimation (SP)
|
100% |
8145
9.50 IPS |
|
Pose Estimation (HP)
|
100% |
88245
103.0 IPS |
|
Pose Estimation (Q)
|
94% |
134098
157.3 IPS |
|
Object Detection (SP)
|
100% |
1494
118.5 IPS |
|
Object Detection (HP)
|
100% |
8141
645.8 IPS |
|
Object Detection (Q)
|
93% |
9995
797.5 IPS |
|
Face Detection (SP)
|
100% |
2274
27.0 IPS |
|
Face Detection (HP)
|
100% |
11194
133.0 IPS |
|
Face Detection (Q)
|
100% |
13488
160.3 IPS |
|
Depth Estimation (SP)
|
100% |
4718
36.4 IPS |
|
Depth Estimation (HP)
|
99% |
42466
327.2 IPS |
|
Depth Estimation (Q)
|
97% |
49225
380.6 IPS |
|
Style Transfer (SP)
|
100% |
12475
16.0 IPS |
|
Style Transfer (HP)
|
100% |
127589
164.0 IPS |
|
Style Transfer (Q)
|
100% |
128484
165.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
4054
149.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
18478
682.3 IPS |
|
Image Super-Resolution (Q)
|
98% |
25154
931.9 IPS |
|
Text Classification (SP)
|
100% |
1841
2.46 KIPS |
|
Text Classification (HP)
|
71% |
4538
6.52 KIPS |
|
Text Classification (Q)
|
69% |
4393
6.44 KIPS |
|
Machine Translation (SP)
|
100% |
1935
33.3 IPS |
|
Machine Translation (HP)
|
100% |
2348
40.4 IPS |
|
Machine Translation (Q)
|
98% |
2338
40.4 IPS |