User | darios |
Upload Date | December 22 2024 09:48 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 18.2 |
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% |
1980
368.2 IPS |
|
Image Classification (HP)
|
100% |
15206
2.83 KIPS |
|
Image Classification (Q)
|
97% |
20422
3.81 KIPS |
|
Image Segmentation (SP)
|
100% |
1890
30.6 IPS |
|
Image Segmentation (HP)
|
100% |
18144
294.1 IPS |
|
Image Segmentation (Q)
|
99% |
23954
388.3 IPS |
|
Pose Estimation (SP)
|
100% |
8389
9.79 IPS |
|
Pose Estimation (HP)
|
100% |
149730
174.7 IPS |
|
Pose Estimation (Q)
|
95% |
292403
342.7 IPS |
|
Object Detection (SP)
|
100% |
2105
166.9 IPS |
|
Object Detection (HP)
|
100% |
16255
1.29 KIPS |
|
Object Detection (Q)
|
91% |
22575
1.80 KIPS |
|
Face Detection (SP)
|
100% |
3484
41.4 IPS |
|
Face Detection (HP)
|
100% |
41214
489.7 IPS |
|
Face Detection (Q)
|
100% |
58375
693.6 IPS |
|
Depth Estimation (SP)
|
100% |
7542
58.1 IPS |
|
Depth Estimation (HP)
|
99% |
95128
732.9 IPS |
|
Depth Estimation (Q)
|
85% |
160030
1.25 KIPS |
|
Style Transfer (SP)
|
100% |
23108
29.7 IPS |
|
Style Transfer (HP)
|
100% |
245113
315.1 IPS |
|
Style Transfer (Q)
|
96% |
306357
395.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
5491
202.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
51606
1.91 KIPS |
|
Image Super-Resolution (Q)
|
99% |
85421
3.15 KIPS |
|
Text Classification (SP)
|
100% |
3433
4.58 KIPS |
|
Text Classification (HP)
|
100% |
4517
6.03 KIPS |
|
Text Classification (Q)
|
93% |
3436
4.61 KIPS |
|
Machine Translation (SP)
|
100% |
3783
65.2 IPS |
|
Machine Translation (HP)
|
100% |
9267
159.6 IPS |
|
Machine Translation (Q)
|
98% |
11326
195.7 IPS |