Upload Date | September 17 2024 04:05 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.1 |
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% |
1653
307.5 IPS |
|
Image Classification (HP)
|
100% |
11414
2.12 KIPS |
|
Image Classification (Q)
|
97% |
14969
2.79 KIPS |
|
Image Segmentation (SP)
|
100% |
1617
26.2 IPS |
|
Image Segmentation (HP)
|
100% |
12851
208.3 IPS |
|
Image Segmentation (Q)
|
99% |
16023
259.7 IPS |
|
Pose Estimation (SP)
|
100% |
8058
9.40 IPS |
|
Pose Estimation (HP)
|
100% |
105825
123.5 IPS |
|
Pose Estimation (Q)
|
95% |
201895
236.6 IPS |
|
Object Detection (SP)
|
100% |
1793
142.2 IPS |
|
Object Detection (HP)
|
100% |
13792
1.09 KIPS |
|
Object Detection (Q)
|
91% |
19139
1.53 KIPS |
|
Face Detection (SP)
|
100% |
3135
37.2 IPS |
|
Face Detection (HP)
|
100% |
33336
396.1 IPS |
|
Face Detection (Q)
|
100% |
48850
580.4 IPS |
|
Depth Estimation (SP)
|
100% |
7144
55.0 IPS |
|
Depth Estimation (HP)
|
99% |
78209
602.6 IPS |
|
Depth Estimation (Q)
|
85% |
127934
1.00 KIPS |
|
Style Transfer (SP)
|
100% |
20699
26.6 IPS |
|
Style Transfer (HP)
|
100% |
138161
177.6 IPS |
|
Style Transfer (Q)
|
96% |
164604
212.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
4952
182.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
33645
1.24 KIPS |
|
Image Super-Resolution (Q)
|
99% |
57440
2.12 KIPS |
|
Text Classification (SP)
|
100% |
3201
4.27 KIPS |
|
Text Classification (HP)
|
100% |
3068
4.09 KIPS |
|
Text Classification (Q)
|
93% |
2813
3.78 KIPS |
|
Machine Translation (SP)
|
100% |
3106
53.5 IPS |
|
Machine Translation (HP)
|
100% |
5998
103.3 IPS |
|
Machine Translation (Q)
|
98% |
7410
128.1 IPS |