Upload Date | September 19 2024 08:25 AM |
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% |
1721
320.0 IPS |
|
Image Classification (HP)
|
100% |
11154
2.07 KIPS |
|
Image Classification (Q)
|
97% |
15356
2.87 KIPS |
|
Image Segmentation (SP)
|
100% |
1618
26.2 IPS |
|
Image Segmentation (HP)
|
100% |
12854
208.4 IPS |
|
Image Segmentation (Q)
|
99% |
16044
260.1 IPS |
|
Pose Estimation (SP)
|
100% |
8307
9.69 IPS |
|
Pose Estimation (HP)
|
100% |
106986
124.8 IPS |
|
Pose Estimation (Q)
|
95% |
206000
241.4 IPS |
|
Object Detection (SP)
|
100% |
1811
143.6 IPS |
|
Object Detection (HP)
|
100% |
13751
1.09 KIPS |
|
Object Detection (Q)
|
91% |
19152
1.53 KIPS |
|
Face Detection (SP)
|
100% |
3204
38.1 IPS |
|
Face Detection (HP)
|
100% |
33549
398.6 IPS |
|
Face Detection (Q)
|
100% |
49063
583.0 IPS |
|
Depth Estimation (SP)
|
100% |
7240
55.8 IPS |
|
Depth Estimation (HP)
|
99% |
78739
606.6 IPS |
|
Depth Estimation (Q)
|
85% |
129329
1.01 KIPS |
|
Style Transfer (SP)
|
100% |
21449
27.6 IPS |
|
Style Transfer (HP)
|
100% |
204687
263.1 IPS |
|
Style Transfer (Q)
|
96% |
245989
317.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
4998
184.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
34439
1.27 KIPS |
|
Image Super-Resolution (Q)
|
99% |
58089
2.14 KIPS |
|
Text Classification (SP)
|
100% |
3259
4.35 KIPS |
|
Text Classification (HP)
|
100% |
2884
3.85 KIPS |
|
Text Classification (Q)
|
93% |
2101
2.82 KIPS |
|
Machine Translation (SP)
|
100% |
3095
53.3 IPS |
|
Machine Translation (HP)
|
100% |
6125
105.5 IPS |
|
Machine Translation (Q)
|
98% |
7162
123.8 IPS |