Upload Date | September 18 2024 02:33 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.0 |
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% |
1696
315.4 IPS |
|
Image Classification (HP)
|
100% |
11885
2.21 KIPS |
|
Image Classification (Q)
|
97% |
16276
3.04 KIPS |
|
Image Segmentation (SP)
|
100% |
1687
27.4 IPS |
|
Image Segmentation (HP)
|
100% |
12883
208.8 IPS |
|
Image Segmentation (Q)
|
99% |
16004
259.4 IPS |
|
Pose Estimation (SP)
|
100% |
7899
9.22 IPS |
|
Pose Estimation (HP)
|
100% |
106566
124.3 IPS |
|
Pose Estimation (Q)
|
95% |
204803
240.0 IPS |
|
Object Detection (SP)
|
100% |
1790
142.0 IPS |
|
Object Detection (HP)
|
100% |
13816
1.10 KIPS |
|
Object Detection (Q)
|
91% |
19244
1.54 KIPS |
|
Face Detection (SP)
|
100% |
3166
37.6 IPS |
|
Face Detection (HP)
|
100% |
33509
398.2 IPS |
|
Face Detection (Q)
|
100% |
49315
586.0 IPS |
|
Depth Estimation (SP)
|
100% |
7087
54.6 IPS |
|
Depth Estimation (HP)
|
99% |
78830
607.3 IPS |
|
Depth Estimation (Q)
|
85% |
127230
994.7 IPS |
|
Style Transfer (SP)
|
100% |
20799
26.7 IPS |
|
Style Transfer (HP)
|
100% |
203524
261.6 IPS |
|
Style Transfer (Q)
|
96% |
246050
317.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
4867
179.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
34987
1.29 KIPS |
|
Image Super-Resolution (Q)
|
99% |
56598
2.09 KIPS |
|
Text Classification (SP)
|
100% |
3198
4.27 KIPS |
|
Text Classification (HP)
|
100% |
2852
3.81 KIPS |
|
Text Classification (Q)
|
93% |
3021
4.05 KIPS |
|
Machine Translation (SP)
|
100% |
3109
53.6 IPS |
|
Machine Translation (HP)
|
100% |
6143
105.8 IPS |
|
Machine Translation (Q)
|
98% |
7542
130.3 IPS |