User | amoudruz |
Upload Date | December 03 2024 12:49 PM |
Views | 5 |
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% |
2005
372.9 IPS |
|
Image Classification (HP)
|
100% |
15495
2.88 KIPS |
|
Image Classification (Q)
|
97% |
20393
3.81 KIPS |
|
Image Segmentation (SP)
|
100% |
1925
31.2 IPS |
|
Image Segmentation (HP)
|
100% |
18314
296.9 IPS |
|
Image Segmentation (Q)
|
99% |
24014
389.3 IPS |
|
Pose Estimation (SP)
|
100% |
8648
10.1 IPS |
|
Pose Estimation (HP)
|
100% |
153848
179.5 IPS |
|
Pose Estimation (Q)
|
95% |
292802
343.2 IPS |
|
Object Detection (SP)
|
100% |
2134
169.3 IPS |
|
Object Detection (HP)
|
100% |
16254
1.29 KIPS |
|
Object Detection (Q)
|
91% |
22476
1.80 KIPS |
|
Face Detection (SP)
|
100% |
3591
42.7 IPS |
|
Face Detection (HP)
|
100% |
41972
498.7 IPS |
|
Face Detection (Q)
|
100% |
57836
687.2 IPS |
|
Depth Estimation (SP)
|
100% |
7683
59.2 IPS |
|
Depth Estimation (HP)
|
99% |
95052
732.3 IPS |
|
Depth Estimation (Q)
|
85% |
160455
1.25 KIPS |
|
Style Transfer (SP)
|
100% |
23333
30.0 IPS |
|
Style Transfer (HP)
|
100% |
245318
315.4 IPS |
|
Style Transfer (Q)
|
96% |
301565
389.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
5557
205.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
52209
1.93 KIPS |
|
Image Super-Resolution (Q)
|
99% |
85755
3.17 KIPS |
|
Text Classification (SP)
|
100% |
3424
4.57 KIPS |
|
Text Classification (HP)
|
100% |
4290
5.73 KIPS |
|
Text Classification (Q)
|
93% |
4323
5.80 KIPS |
|
Machine Translation (SP)
|
100% |
3757
64.7 IPS |
|
Machine Translation (HP)
|
100% |
9456
162.9 IPS |
|
Machine Translation (Q)
|
98% |
11436
197.6 IPS |