Upload Date | January 02 2025 10:03 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 18.2 |
Model | iPhone 16 Pro |
Model ID | iPhone17,1 |
Motherboard | D93AP |
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 | 7.48 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1963
365.1 IPS |
|
Image Classification (HP)
|
100% |
15292
2.84 KIPS |
|
Image Classification (Q)
|
97% |
20623
3.85 KIPS |
|
Image Segmentation (SP)
|
100% |
1868
30.3 IPS |
|
Image Segmentation (HP)
|
100% |
18123
293.8 IPS |
|
Image Segmentation (Q)
|
99% |
23970
388.6 IPS |
|
Pose Estimation (SP)
|
100% |
7672
8.95 IPS |
|
Pose Estimation (HP)
|
100% |
119616
139.6 IPS |
|
Pose Estimation (Q)
|
95% |
286965
336.3 IPS |
|
Object Detection (SP)
|
100% |
1753
139.1 IPS |
|
Object Detection (HP)
|
100% |
16251
1.29 KIPS |
|
Object Detection (Q)
|
91% |
22408
1.79 KIPS |
|
Face Detection (SP)
|
100% |
3302
39.2 IPS |
|
Face Detection (HP)
|
100% |
40912
486.1 IPS |
|
Face Detection (Q)
|
100% |
57104
678.5 IPS |
|
Depth Estimation (SP)
|
100% |
7474
57.6 IPS |
|
Depth Estimation (HP)
|
99% |
94165
725.5 IPS |
|
Depth Estimation (Q)
|
85% |
159658
1.25 KIPS |
|
Style Transfer (SP)
|
100% |
22132
28.5 IPS |
|
Style Transfer (HP)
|
100% |
244888
314.8 IPS |
|
Style Transfer (Q)
|
96% |
298603
385.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
4539
167.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
47360
1.75 KIPS |
|
Image Super-Resolution (Q)
|
99% |
80879
2.99 KIPS |
|
Text Classification (SP)
|
100% |
2789
3.72 KIPS |
|
Text Classification (HP)
|
100% |
4540
6.06 KIPS |
|
Text Classification (Q)
|
93% |
4310
5.78 KIPS |
|
Machine Translation (SP)
|
100% |
2283
39.3 IPS |
|
Machine Translation (HP)
|
100% |
6114
105.3 IPS |
|
Machine Translation (Q)
|
98% |
8651
149.5 IPS |