User | UHI |
Upload Date | December 21 2024 03:02 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 |
System Information | |
---|---|
Operating System | iOS 18.2 |
Model | iPhone 16 |
Model ID | iPhone17,3 |
Motherboard | D47AP |
CPU Information | |
---|---|
Name | Apple A18 |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 4.04 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.51 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1948
362.2 IPS |
|
Image Classification (HP)
|
100% |
15324
2.85 KIPS |
|
Image Classification (Q)
|
97% |
21152
3.95 KIPS |
|
Image Segmentation (SP)
|
100% |
1802
29.2 IPS |
|
Image Segmentation (HP)
|
100% |
18101
293.4 IPS |
|
Image Segmentation (Q)
|
99% |
23897
387.4 IPS |
|
Pose Estimation (SP)
|
100% |
9249
10.8 IPS |
|
Pose Estimation (HP)
|
100% |
155019
180.9 IPS |
|
Pose Estimation (Q)
|
95% |
295209
346.0 IPS |
|
Object Detection (SP)
|
100% |
2179
172.8 IPS |
|
Object Detection (HP)
|
100% |
16340
1.30 KIPS |
|
Object Detection (Q)
|
91% |
22783
1.82 KIPS |
|
Face Detection (SP)
|
100% |
3360
39.9 IPS |
|
Face Detection (HP)
|
100% |
39998
475.3 IPS |
|
Face Detection (Q)
|
100% |
57183
679.5 IPS |
|
Depth Estimation (SP)
|
100% |
7933
61.1 IPS |
|
Depth Estimation (HP)
|
99% |
96518
743.6 IPS |
|
Depth Estimation (Q)
|
85% |
162257
1.27 KIPS |
|
Style Transfer (SP)
|
100% |
23975
30.8 IPS |
|
Style Transfer (HP)
|
100% |
245380
315.4 IPS |
|
Style Transfer (Q)
|
96% |
302480
390.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
5621
207.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
50173
1.85 KIPS |
|
Image Super-Resolution (Q)
|
99% |
87497
3.23 KIPS |
|
Text Classification (SP)
|
100% |
3430
4.58 KIPS |
|
Text Classification (HP)
|
100% |
4751
6.34 KIPS |
|
Text Classification (Q)
|
93% |
4372
5.87 KIPS |
|
Machine Translation (SP)
|
100% |
3600
62.0 IPS |
|
Machine Translation (HP)
|
100% |
10274
177.0 IPS |
|
Machine Translation (Q)
|
98% |
11711
202.4 IPS |