User | danfah |
Upload Date | August 19 2024 06:49 AM |
Views | 3 |
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% |
1727
321.2 IPS |
|
Image Classification (HP)
|
100% |
10448
1.94 KIPS |
|
Image Classification (Q)
|
99% |
12678
2.36 KIPS |
|
Image Segmentation (SP)
|
100% |
1616
26.2 IPS |
|
Image Segmentation (HP)
|
100% |
10620
172.2 IPS |
|
Image Segmentation (Q)
|
100% |
10789
174.9 IPS |
|
Pose Estimation (SP)
|
100% |
8569
10.00 IPS |
|
Pose Estimation (HP)
|
100% |
102940
120.1 IPS |
|
Pose Estimation (Q)
|
94% |
199325
233.8 IPS |
|
Object Detection (SP)
|
100% |
1831
145.2 IPS |
|
Object Detection (HP)
|
100% |
12859
1.02 KIPS |
|
Object Detection (Q)
|
91% |
18565
1.48 KIPS |
|
Face Detection (SP)
|
100% |
3224
38.3 IPS |
|
Face Detection (HP)
|
100% |
21738
258.3 IPS |
|
Face Detection (Q)
|
100% |
36864
438.0 IPS |
|
Depth Estimation (SP)
|
100% |
7290
56.2 IPS |
|
Depth Estimation (HP)
|
99% |
65099
501.5 IPS |
|
Depth Estimation (Q)
|
97% |
73841
571.0 IPS |
|
Style Transfer (SP)
|
100% |
21872
28.1 IPS |
|
Style Transfer (HP)
|
100% |
137932
177.3 IPS |
|
Style Transfer (Q)
|
100% |
137718
177.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
5190
191.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
36141
1.33 KIPS |
|
Image Super-Resolution (Q)
|
98% |
61550
2.28 KIPS |
|
Text Classification (SP)
|
100% |
3229
4.31 KIPS |
|
Text Classification (HP)
|
100% |
1776
2.37 KIPS |
|
Text Classification (Q)
|
93% |
1710
2.29 KIPS |
|
Machine Translation (SP)
|
100% |
2982
51.4 IPS |
|
Machine Translation (HP)
|
100% |
5698
98.2 IPS |
|
Machine Translation (Q)
|
98% |
6236
107.8 IPS |