User | Kozek |
Upload Date | December 05 2024 10:12 PM |
Views | 8 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 18.1.1 |
Model | iPhone 16 Pro |
Model ID | iPhone17,1 |
Motherboard | D93AP |
CPU Information | |
---|---|
Name | Apple A18 Pro |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 4.04 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.49 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2019
375.5 IPS |
|
Image Classification (HP)
|
100% |
15249
2.84 KIPS |
|
Image Classification (Q)
|
97% |
20693
3.86 KIPS |
|
Image Segmentation (SP)
|
100% |
1943
31.5 IPS |
|
Image Segmentation (HP)
|
100% |
18407
298.4 IPS |
|
Image Segmentation (Q)
|
99% |
24129
391.1 IPS |
|
Pose Estimation (SP)
|
100% |
8531
9.95 IPS |
|
Pose Estimation (HP)
|
100% |
153066
178.6 IPS |
|
Pose Estimation (Q)
|
95% |
293978
344.6 IPS |
|
Object Detection (SP)
|
100% |
2140
169.7 IPS |
|
Object Detection (HP)
|
100% |
16272
1.29 KIPS |
|
Object Detection (Q)
|
91% |
22479
1.80 KIPS |
|
Face Detection (SP)
|
100% |
3670
43.6 IPS |
|
Face Detection (HP)
|
100% |
41260
490.3 IPS |
|
Face Detection (Q)
|
100% |
58308
692.8 IPS |
|
Depth Estimation (SP)
|
100% |
7658
59.0 IPS |
|
Depth Estimation (HP)
|
99% |
95155
733.1 IPS |
|
Depth Estimation (Q)
|
85% |
161096
1.26 KIPS |
|
Style Transfer (SP)
|
100% |
23632
30.4 IPS |
|
Style Transfer (HP)
|
100% |
246009
316.2 IPS |
|
Style Transfer (Q)
|
96% |
303109
391.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
5642
208.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
50437
1.86 KIPS |
|
Image Super-Resolution (Q)
|
99% |
84452
3.12 KIPS |
|
Text Classification (SP)
|
100% |
3421
4.57 KIPS |
|
Text Classification (HP)
|
100% |
4656
6.21 KIPS |
|
Text Classification (Q)
|
93% |
5033
6.75 KIPS |
|
Machine Translation (SP)
|
100% |
3862
66.5 IPS |
|
Machine Translation (HP)
|
100% |
9755
168.0 IPS |
|
Machine Translation (Q)
|
98% |
11409
197.2 IPS |