Upload Date | November 10 2024 11:35 PM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.2 |
Model | iPhone 15 Pro Max |
Model ID | iPhone16,2 |
Motherboard | D84AP |
CPU Information | |
---|---|
Name | Apple A17 Pro |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.78 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.48 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1601
297.7 IPS |
|
Image Classification (HP)
|
100% |
11334
2.11 KIPS |
|
Image Classification (Q)
|
97% |
14715
2.75 KIPS |
|
Image Segmentation (SP)
|
100% |
1520
24.6 IPS |
|
Image Segmentation (HP)
|
100% |
15786
255.9 IPS |
|
Image Segmentation (Q)
|
99% |
20200
327.5 IPS |
|
Pose Estimation (SP)
|
100% |
6496
7.58 IPS |
|
Pose Estimation (HP)
|
100% |
92978
108.5 IPS |
|
Pose Estimation (Q)
|
95% |
192006
225.0 IPS |
|
Object Detection (SP)
|
100% |
1605
127.3 IPS |
|
Object Detection (HP)
|
100% |
13853
1.10 KIPS |
|
Object Detection (Q)
|
91% |
18975
1.52 KIPS |
|
Face Detection (SP)
|
100% |
2745
32.6 IPS |
|
Face Detection (HP)
|
100% |
33656
399.9 IPS |
|
Face Detection (Q)
|
100% |
50280
597.4 IPS |
|
Depth Estimation (SP)
|
100% |
6063
46.7 IPS |
|
Depth Estimation (HP)
|
99% |
76761
591.4 IPS |
|
Depth Estimation (Q)
|
85% |
120632
943.2 IPS |
|
Style Transfer (SP)
|
100% |
17410
22.4 IPS |
|
Style Transfer (HP)
|
100% |
186098
239.2 IPS |
|
Style Transfer (Q)
|
96% |
250138
322.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
3968
146.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
32574
1.20 KIPS |
|
Image Super-Resolution (Q)
|
99% |
55995
2.07 KIPS |
|
Text Classification (SP)
|
100% |
3151
4.21 KIPS |
|
Text Classification (HP)
|
100% |
2122
2.83 KIPS |
|
Text Classification (Q)
|
93% |
1942
2.61 KIPS |
|
Machine Translation (SP)
|
100% |
3089
53.2 IPS |
|
Machine Translation (HP)
|
100% |
6372
109.8 IPS |
|
Machine Translation (Q)
|
98% |
7501
129.6 IPS |