User | iGeneration |
Upload Date | December 30 2024 11:27 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 18.1.1 |
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 | 7.47 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1998
371.6 IPS |
|
Image Classification (HP)
|
100% |
15840
2.95 KIPS |
|
Image Classification (Q)
|
97% |
21129
3.94 KIPS |
|
Image Segmentation (SP)
|
100% |
1931
31.3 IPS |
|
Image Segmentation (HP)
|
100% |
18211
295.2 IPS |
|
Image Segmentation (Q)
|
99% |
24072
390.2 IPS |
|
Pose Estimation (SP)
|
100% |
8715
10.2 IPS |
|
Pose Estimation (HP)
|
100% |
154266
180.0 IPS |
|
Pose Estimation (Q)
|
95% |
293436
343.9 IPS |
|
Object Detection (SP)
|
100% |
2103
166.8 IPS |
|
Object Detection (HP)
|
100% |
16354
1.30 KIPS |
|
Object Detection (Q)
|
91% |
23080
1.84 KIPS |
|
Face Detection (SP)
|
100% |
3433
40.8 IPS |
|
Face Detection (HP)
|
100% |
41913
498.0 IPS |
|
Face Detection (Q)
|
100% |
58225
691.8 IPS |
|
Depth Estimation (SP)
|
100% |
7739
59.6 IPS |
|
Depth Estimation (HP)
|
99% |
95297
734.2 IPS |
|
Depth Estimation (Q)
|
85% |
162090
1.27 KIPS |
|
Style Transfer (SP)
|
100% |
23535
30.3 IPS |
|
Style Transfer (HP)
|
100% |
245465
315.5 IPS |
|
Style Transfer (Q)
|
96% |
304867
393.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
5575
205.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
50406
1.86 KIPS |
|
Image Super-Resolution (Q)
|
99% |
85005
3.14 KIPS |
|
Text Classification (SP)
|
100% |
3447
4.60 KIPS |
|
Text Classification (HP)
|
100% |
4489
5.99 KIPS |
|
Text Classification (Q)
|
93% |
4419
5.93 KIPS |
|
Machine Translation (SP)
|
100% |
3741
64.4 IPS |
|
Machine Translation (HP)
|
100% |
9410
162.1 IPS |
|
Machine Translation (Q)
|
98% |
11381
196.7 IPS |