User | M91 |
Upload Date | August 22 2024 12:20 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.1 |
Model | iPhone 15 Pro |
Model ID | iPhone16,1 |
Motherboard | D83AP |
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 | 7.51 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1642
305.4 IPS |
|
Image Classification (HP)
|
100% |
10608
1.97 KIPS |
|
Image Classification (Q)
|
99% |
12482
2.33 KIPS |
|
Image Segmentation (SP)
|
100% |
1580
25.6 IPS |
|
Image Segmentation (HP)
|
100% |
10909
176.9 IPS |
|
Image Segmentation (Q)
|
100% |
10846
175.8 IPS |
|
Pose Estimation (SP)
|
100% |
6990
8.16 IPS |
|
Pose Estimation (HP)
|
100% |
98085
114.4 IPS |
|
Pose Estimation (Q)
|
94% |
197101
231.2 IPS |
|
Object Detection (SP)
|
100% |
1726
136.9 IPS |
|
Object Detection (HP)
|
100% |
12928
1.03 KIPS |
|
Object Detection (Q)
|
91% |
18275
1.46 KIPS |
|
Face Detection (SP)
|
100% |
3128
37.2 IPS |
|
Face Detection (HP)
|
100% |
21794
259.0 IPS |
|
Face Detection (Q)
|
100% |
36504
433.8 IPS |
|
Depth Estimation (SP)
|
100% |
6751
52.0 IPS |
|
Depth Estimation (HP)
|
99% |
64658
498.1 IPS |
|
Depth Estimation (Q)
|
97% |
75177
581.3 IPS |
|
Style Transfer (SP)
|
100% |
19512
25.1 IPS |
|
Style Transfer (HP)
|
100% |
137610
176.9 IPS |
|
Style Transfer (Q)
|
100% |
138375
177.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
4580
169.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
33940
1.25 KIPS |
|
Image Super-Resolution (Q)
|
98% |
55230
2.05 KIPS |
|
Text Classification (SP)
|
100% |
3100
4.14 KIPS |
|
Text Classification (HP)
|
100% |
3284
4.38 KIPS |
|
Text Classification (Q)
|
93% |
2419
3.25 KIPS |
|
Machine Translation (SP)
|
100% |
3127
53.9 IPS |
|
Machine Translation (HP)
|
100% |
6018
103.7 IPS |
|
Machine Translation (Q)
|
98% |
7492
129.5 IPS |