User | barcellos |
Upload Date | August 17 2024 01:46 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 17.6.1 |
Model | iPhone 14 Pro |
Model ID | iPhone15,2 |
Motherboard | D73AP |
CPU Information | |
---|---|
Name | Apple A16 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.46 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 5.50 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1236
229.8 IPS |
|
Image Classification (HP)
|
100% |
5848
1.09 KIPS |
|
Image Classification (Q)
|
99% |
5854
1.09 KIPS |
|
Image Segmentation (SP)
|
100% |
731
11.9 IPS |
|
Image Segmentation (HP)
|
100% |
5151
83.5 IPS |
|
Image Segmentation (Q)
|
100% |
4787
77.6 IPS |
|
Pose Estimation (SP)
|
100% |
6139
7.16 IPS |
|
Pose Estimation (HP)
|
100% |
81297
94.9 IPS |
|
Pose Estimation (Q)
|
94% |
71030
83.3 IPS |
|
Object Detection (SP)
|
100% |
1190
94.4 IPS |
|
Object Detection (HP)
|
100% |
7726
612.9 IPS |
|
Object Detection (Q)
|
93% |
8443
673.7 IPS |
|
Face Detection (SP)
|
100% |
2163
25.7 IPS |
|
Face Detection (HP)
|
100% |
11149
132.5 IPS |
|
Face Detection (Q)
|
100% |
12978
154.2 IPS |
|
Depth Estimation (SP)
|
100% |
4185
32.2 IPS |
|
Depth Estimation (HP)
|
99% |
40481
311.9 IPS |
|
Depth Estimation (Q)
|
97% |
46215
357.3 IPS |
|
Style Transfer (SP)
|
100% |
11219
14.4 IPS |
|
Style Transfer (HP)
|
100% |
121296
155.9 IPS |
|
Style Transfer (Q)
|
100% |
122144
157.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
3259
120.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
16278
601.1 IPS |
|
Image Super-Resolution (Q)
|
98% |
19897
737.1 IPS |
|
Text Classification (SP)
|
100% |
1366
1.82 KIPS |
|
Text Classification (HP)
|
100% |
3401
4.54 KIPS |
|
Text Classification (Q)
|
93% |
3266
4.38 KIPS |
|
Machine Translation (SP)
|
100% |
1643
28.3 IPS |
|
Machine Translation (HP)
|
100% |
2314
39.9 IPS |
|
Machine Translation (Q)
|
98% |
2313
40.0 IPS |