User | mamiyoshi |
Upload Date | March 18 2025 10:07 AM |
Views | 10 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 18.4 |
Model | iPhone 16 Pro Max |
Model ID | iPhone17,2 |
Motherboard | D94AP |
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 | 7.45 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2060
383.1 IPS |
|
Image Classification (HP)
|
100% |
14650
2.72 KIPS |
|
Image Classification (Q)
|
97% |
19898
3.71 KIPS |
|
Image Segmentation (SP)
|
100% |
1970
31.9 IPS |
|
Image Segmentation (HP)
|
100% |
18100
293.4 IPS |
|
Image Segmentation (Q)
|
99% |
23835
386.4 IPS |
|
Pose Estimation (SP)
|
100% |
9534
11.1 IPS |
|
Pose Estimation (HP)
|
100% |
153060
178.6 IPS |
|
Pose Estimation (Q)
|
95% |
291160
341.3 IPS |
|
Object Detection (SP)
|
100% |
2358
187.0 IPS |
|
Object Detection (HP)
|
100% |
16036
1.27 KIPS |
|
Object Detection (Q)
|
91% |
22012
1.76 KIPS |
|
Face Detection (SP)
|
100% |
3915
46.5 IPS |
|
Face Detection (HP)
|
100% |
40677
483.3 IPS |
|
Face Detection (Q)
|
100% |
58742
698.0 IPS |
|
Depth Estimation (SP)
|
100% |
8288
63.9 IPS |
|
Depth Estimation (HP)
|
99% |
94096
725.0 IPS |
|
Depth Estimation (Q)
|
85% |
161143
1.26 KIPS |
|
Style Transfer (SP)
|
100% |
21005
27.0 IPS |
|
Style Transfer (HP)
|
100% |
244932
314.9 IPS |
|
Style Transfer (Q)
|
96% |
303254
391.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
5698
210.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
50608
1.87 KIPS |
|
Image Super-Resolution (Q)
|
99% |
85029
3.14 KIPS |
|
Text Classification (SP)
|
100% |
3345
4.46 KIPS |
|
Text Classification (HP)
|
100% |
3224
4.30 KIPS |
|
Text Classification (Q)
|
93% |
2876
3.86 KIPS |
|
Machine Translation (SP)
|
100% |
4192
72.2 IPS |
|
Machine Translation (HP)
|
100% |
9859
169.8 IPS |
|
Machine Translation (Q)
|
98% |
10562
182.5 IPS |