Upload Date | January 05 2025 08:14 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A14 Bionic |
System Information | |
---|---|
Operating System | iOS 18.3 |
Model | iPhone 12 Pro Max |
Model ID | iPhone13,4 |
Motherboard | D54pAP |
CPU Information | |
---|---|
Name | Apple A14 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 2.99 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 5.56 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1260
234.4 IPS |
|
Image Classification (HP)
|
100% |
4385
815.4 IPS |
|
Image Classification (Q)
|
96% |
4506
841.5 IPS |
|
Image Segmentation (SP)
|
100% |
1157
18.8 IPS |
|
Image Segmentation (HP)
|
100% |
8800
142.7 IPS |
|
Image Segmentation (Q)
|
99% |
8549
138.6 IPS |
|
Pose Estimation (SP)
|
100% |
5180
6.04 IPS |
|
Pose Estimation (HP)
|
100% |
60734
70.9 IPS |
|
Pose Estimation (Q)
|
95% |
62371
73.1 IPS |
|
Object Detection (SP)
|
100% |
1304
103.4 IPS |
|
Object Detection (HP)
|
99% |
6330
503.5 IPS |
|
Object Detection (Q)
|
91% |
5929
473.8 IPS |
|
Face Detection (SP)
|
100% |
2592
30.8 IPS |
|
Face Detection (HP)
|
100% |
15342
182.3 IPS |
|
Face Detection (Q)
|
100% |
12082
143.6 IPS |
|
Depth Estimation (SP)
|
100% |
4872
37.5 IPS |
|
Depth Estimation (HP)
|
99% |
39156
301.7 IPS |
|
Depth Estimation (Q)
|
85% |
43435
339.4 IPS |
|
Style Transfer (SP)
|
100% |
13580
17.5 IPS |
|
Style Transfer (HP)
|
100% |
97389
125.2 IPS |
|
Style Transfer (Q)
|
96% |
93511
120.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
2907
107.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
17951
662.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
18411
679.9 IPS |
|
Text Classification (SP)
|
100% |
2121
2.83 KIPS |
|
Text Classification (HP)
|
100% |
2172
2.90 KIPS |
|
Text Classification (Q)
|
93% |
2176
2.92 KIPS |
|
Machine Translation (SP)
|
100% |
2272
39.1 IPS |
|
Machine Translation (HP)
|
100% |
4500
77.5 IPS |
|
Machine Translation (Q)
|
98% |
5579
96.4 IPS |