User | natehsu |
Upload Date | December 19 2024 02:44 PM |
Views | 7 |
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% |
2003
372.5 IPS |
|
Image Classification (HP)
|
100% |
15080
2.80 KIPS |
|
Image Classification (Q)
|
97% |
20326
3.79 KIPS |
|
Image Segmentation (SP)
|
100% |
1960
31.8 IPS |
|
Image Segmentation (HP)
|
100% |
18316
296.9 IPS |
|
Image Segmentation (Q)
|
99% |
24089
390.5 IPS |
|
Pose Estimation (SP)
|
100% |
9147
10.7 IPS |
|
Pose Estimation (HP)
|
100% |
154683
180.5 IPS |
|
Pose Estimation (Q)
|
95% |
294317
345.0 IPS |
|
Object Detection (SP)
|
100% |
2153
170.8 IPS |
|
Object Detection (HP)
|
100% |
16249
1.29 KIPS |
|
Object Detection (Q)
|
91% |
22373
1.79 KIPS |
|
Face Detection (SP)
|
100% |
3631
43.1 IPS |
|
Face Detection (HP)
|
100% |
41761
496.2 IPS |
|
Face Detection (Q)
|
100% |
58059
689.9 IPS |
|
Depth Estimation (SP)
|
100% |
7991
61.6 IPS |
|
Depth Estimation (HP)
|
99% |
95218
733.6 IPS |
|
Depth Estimation (Q)
|
85% |
163141
1.28 KIPS |
|
Style Transfer (SP)
|
100% |
24673
31.7 IPS |
|
Style Transfer (HP)
|
100% |
245233
315.3 IPS |
|
Style Transfer (Q)
|
96% |
302348
390.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
5747
212.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
49931
1.84 KIPS |
|
Image Super-Resolution (Q)
|
99% |
84440
3.12 KIPS |
|
Text Classification (SP)
|
100% |
3423
4.57 KIPS |
|
Text Classification (HP)
|
100% |
4629
6.18 KIPS |
|
Text Classification (Q)
|
93% |
4756
6.38 KIPS |
|
Machine Translation (SP)
|
100% |
3779
65.1 IPS |
|
Machine Translation (HP)
|
100% |
9308
160.3 IPS |
|
Machine Translation (Q)
|
98% |
11459
198.0 IPS |