User | edsonchan |
Upload Date | May 23 2025 07:26 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 18.5 |
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% |
2049
381.0 IPS |
|
Image Classification (HP)
|
100% |
15074
2.80 KIPS |
|
Image Classification (Q)
|
97% |
21028
3.92 KIPS |
|
Image Segmentation (SP)
|
100% |
1934
31.3 IPS |
|
Image Segmentation (HP)
|
100% |
18258
296.0 IPS |
|
Image Segmentation (Q)
|
99% |
24044
389.8 IPS |
|
Pose Estimation (SP)
|
100% |
8937
10.4 IPS |
|
Pose Estimation (HP)
|
100% |
151421
176.7 IPS |
|
Pose Estimation (Q)
|
95% |
290980
341.0 IPS |
|
Object Detection (SP)
|
100% |
2327
184.6 IPS |
|
Object Detection (HP)
|
100% |
16272
1.29 KIPS |
|
Object Detection (Q)
|
91% |
22647
1.81 KIPS |
|
Face Detection (SP)
|
100% |
3871
46.0 IPS |
|
Face Detection (HP)
|
100% |
41202
489.6 IPS |
|
Face Detection (Q)
|
100% |
58205
691.6 IPS |
|
Depth Estimation (SP)
|
100% |
8167
62.9 IPS |
|
Depth Estimation (HP)
|
99% |
95193
733.4 IPS |
|
Depth Estimation (Q)
|
85% |
159916
1.25 KIPS |
|
Style Transfer (SP)
|
100% |
19969
25.7 IPS |
|
Style Transfer (HP)
|
100% |
245549
315.7 IPS |
|
Style Transfer (Q)
|
96% |
301201
388.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
5452
201.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
51979
1.92 KIPS |
|
Image Super-Resolution (Q)
|
99% |
85898
3.17 KIPS |
|
Text Classification (SP)
|
100% |
3379
4.51 KIPS |
|
Text Classification (HP)
|
100% |
5033
6.72 KIPS |
|
Text Classification (Q)
|
93% |
4915
6.60 KIPS |
|
Machine Translation (SP)
|
100% |
4206
72.5 IPS |
|
Machine Translation (HP)
|
100% |
10070
173.5 IPS |
|
Machine Translation (Q)
|
98% |
11113
192.0 IPS |