User | 3Dman |
Upload Date | December 03 2024 05:38 AM |
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% |
2004
372.7 IPS |
|
Image Classification (HP)
|
100% |
15369
2.86 KIPS |
|
Image Classification (Q)
|
97% |
19909
3.72 KIPS |
|
Image Segmentation (SP)
|
100% |
1944
31.5 IPS |
|
Image Segmentation (HP)
|
100% |
18302
296.7 IPS |
|
Image Segmentation (Q)
|
99% |
24096
390.6 IPS |
|
Pose Estimation (SP)
|
100% |
8725
10.2 IPS |
|
Pose Estimation (HP)
|
100% |
153778
179.4 IPS |
|
Pose Estimation (Q)
|
95% |
292631
343.0 IPS |
|
Object Detection (SP)
|
100% |
2135
169.3 IPS |
|
Object Detection (HP)
|
100% |
16723
1.33 KIPS |
|
Object Detection (Q)
|
91% |
22275
1.78 KIPS |
|
Face Detection (SP)
|
100% |
3582
42.6 IPS |
|
Face Detection (HP)
|
100% |
41583
494.1 IPS |
|
Face Detection (Q)
|
100% |
57894
687.9 IPS |
|
Depth Estimation (SP)
|
100% |
7646
58.9 IPS |
|
Depth Estimation (HP)
|
99% |
95372
734.8 IPS |
|
Depth Estimation (Q)
|
85% |
160358
1.25 KIPS |
|
Style Transfer (SP)
|
100% |
23044
29.6 IPS |
|
Style Transfer (HP)
|
100% |
245190
315.2 IPS |
|
Style Transfer (Q)
|
96% |
300655
388.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
5546
204.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
49603
1.83 KIPS |
|
Image Super-Resolution (Q)
|
99% |
83249
3.07 KIPS |
|
Text Classification (SP)
|
100% |
3435
4.59 KIPS |
|
Text Classification (HP)
|
100% |
4826
6.44 KIPS |
|
Text Classification (Q)
|
93% |
4976
6.68 KIPS |
|
Machine Translation (SP)
|
100% |
3687
63.5 IPS |
|
Machine Translation (HP)
|
100% |
9767
168.2 IPS |
|
Machine Translation (Q)
|
98% |
11560
199.8 IPS |