Upload Date | January 23 2025 12:56 PM |
Views | 12 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 18.2.1 |
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 | 7.45 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2017
375.1 IPS |
|
Image Classification (HP)
|
100% |
15364
2.86 KIPS |
|
Image Classification (Q)
|
97% |
19127
3.57 KIPS |
|
Image Segmentation (SP)
|
100% |
1946
31.5 IPS |
|
Image Segmentation (HP)
|
100% |
18274
296.2 IPS |
|
Image Segmentation (Q)
|
99% |
24028
389.5 IPS |
|
Pose Estimation (SP)
|
100% |
9203
10.7 IPS |
|
Pose Estimation (HP)
|
100% |
154399
180.2 IPS |
|
Pose Estimation (Q)
|
95% |
294481
345.1 IPS |
|
Object Detection (SP)
|
100% |
2169
172.0 IPS |
|
Object Detection (HP)
|
100% |
16214
1.29 KIPS |
|
Object Detection (Q)
|
91% |
22824
1.82 KIPS |
|
Face Detection (SP)
|
100% |
3624
43.1 IPS |
|
Face Detection (HP)
|
100% |
41197
489.5 IPS |
|
Face Detection (Q)
|
100% |
58130
690.7 IPS |
|
Depth Estimation (SP)
|
100% |
8010
61.7 IPS |
|
Depth Estimation (HP)
|
99% |
95319
734.4 IPS |
|
Depth Estimation (Q)
|
85% |
164319
1.28 KIPS |
|
Style Transfer (SP)
|
100% |
24718
31.8 IPS |
|
Style Transfer (HP)
|
100% |
246158
316.4 IPS |
|
Style Transfer (Q)
|
96% |
302376
390.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
5739
211.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
50623
1.87 KIPS |
|
Image Super-Resolution (Q)
|
99% |
86824
3.21 KIPS |
|
Text Classification (SP)
|
100% |
3429
4.58 KIPS |
|
Text Classification (HP)
|
100% |
4541
6.06 KIPS |
|
Text Classification (Q)
|
93% |
4382
5.88 KIPS |
|
Machine Translation (SP)
|
100% |
3758
64.7 IPS |
|
Machine Translation (HP)
|
100% |
10013
172.5 IPS |
|
Machine Translation (Q)
|
98% |
11462
198.1 IPS |