User | Bhealey |
Upload Date | May 29 2025 02:16 AM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 18.5 |
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 | 7.47 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2065
384.0 IPS |
|
Image Classification (HP)
|
100% |
15697
2.92 KIPS |
|
Image Classification (Q)
|
97% |
21610
4.03 KIPS |
|
Image Segmentation (SP)
|
100% |
2040
33.1 IPS |
|
Image Segmentation (HP)
|
100% |
18282
296.4 IPS |
|
Image Segmentation (Q)
|
99% |
24288
393.7 IPS |
|
Pose Estimation (SP)
|
100% |
8809
10.3 IPS |
|
Pose Estimation (HP)
|
100% |
148938
173.8 IPS |
|
Pose Estimation (Q)
|
95% |
290498
340.5 IPS |
|
Object Detection (SP)
|
100% |
2329
184.7 IPS |
|
Object Detection (HP)
|
100% |
16365
1.30 KIPS |
|
Object Detection (Q)
|
91% |
23091
1.85 KIPS |
|
Face Detection (SP)
|
100% |
3858
45.8 IPS |
|
Face Detection (HP)
|
100% |
41468
492.7 IPS |
|
Face Detection (Q)
|
100% |
59785
710.4 IPS |
|
Depth Estimation (SP)
|
100% |
7993
61.6 IPS |
|
Depth Estimation (HP)
|
99% |
95255
733.9 IPS |
|
Depth Estimation (Q)
|
85% |
159579
1.25 KIPS |
|
Style Transfer (SP)
|
100% |
19528
25.1 IPS |
|
Style Transfer (HP)
|
100% |
245431
315.5 IPS |
|
Style Transfer (Q)
|
96% |
303019
391.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
5263
194.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
50474
1.86 KIPS |
|
Image Super-Resolution (Q)
|
99% |
84769
3.13 KIPS |
|
Text Classification (SP)
|
100% |
3375
4.51 KIPS |
|
Text Classification (HP)
|
100% |
2956
3.95 KIPS |
|
Text Classification (Q)
|
93% |
3249
4.36 KIPS |
|
Machine Translation (SP)
|
100% |
3676
63.3 IPS |
|
Machine Translation (HP)
|
100% |
10118
174.3 IPS |
|
Machine Translation (Q)
|
98% |
11681
201.9 IPS |