User | MaybeHS |
Upload Date | November 09 2024 06:04 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | CPU |
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% |
1718
319.5 IPS |
|
Image Classification (HP)
|
100% |
2921
543.3 IPS |
|
Image Classification (Q)
|
96% |
2018
376.8 IPS |
|
Image Segmentation (SP)
|
100% |
1624
26.3 IPS |
|
Image Segmentation (HP)
|
100% |
2393
38.8 IPS |
|
Image Segmentation (Q)
|
99% |
3086
50.0 IPS |
|
Pose Estimation (SP)
|
100% |
8442
9.85 IPS |
|
Pose Estimation (HP)
|
100% |
16880
19.7 IPS |
|
Pose Estimation (Q)
|
95% |
14602
17.1 IPS |
|
Object Detection (SP)
|
100% |
1804
143.1 IPS |
|
Object Detection (HP)
|
97% |
3363
267.7 IPS |
|
Object Detection (Q)
|
94% |
2358
187.9 IPS |
|
Face Detection (SP)
|
100% |
3206
38.1 IPS |
|
Face Detection (HP)
|
100% |
6790
80.7 IPS |
|
Face Detection (Q)
|
100% |
3891
46.2 IPS |
|
Depth Estimation (SP)
|
100% |
7212
55.6 IPS |
|
Depth Estimation (HP)
|
98% |
13471
104.1 IPS |
|
Depth Estimation (Q)
|
85% |
9353
73.1 IPS |
|
Style Transfer (SP)
|
100% |
21500
27.6 IPS |
|
Style Transfer (HP)
|
100% |
32683
42.0 IPS |
|
Style Transfer (Q)
|
96% |
27589
35.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
5043
186.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
5864
216.5 IPS |
|
Image Super-Resolution (Q)
|
99% |
4446
164.2 IPS |
|
Text Classification (SP)
|
100% |
3205
4.28 KIPS |
|
Text Classification (HP)
|
100% |
5547
7.40 KIPS |
|
Text Classification (Q)
|
93% |
5568
7.47 KIPS |
|
Machine Translation (SP)
|
100% |
3116
53.7 IPS |
|
Machine Translation (HP)
|
98% |
6021
104.0 IPS |
|
Machine Translation (Q)
|
98% |
6066
104.8 IPS |