Upload Date | September 18 2024 09:57 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A14 Bionic |
System Information | |
---|---|
Operating System | iOS 18.1 |
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% |
1231
229.0 IPS |
|
Image Classification (HP)
|
100% |
4383
815.1 IPS |
|
Image Classification (Q)
|
96% |
4752
887.3 IPS |
|
Image Segmentation (SP)
|
100% |
1157
18.8 IPS |
|
Image Segmentation (HP)
|
100% |
5512
89.4 IPS |
|
Image Segmentation (Q)
|
99% |
5715
92.6 IPS |
|
Pose Estimation (SP)
|
100% |
5005
5.84 IPS |
|
Pose Estimation (HP)
|
100% |
62482
72.9 IPS |
|
Pose Estimation (Q)
|
95% |
62816
73.6 IPS |
|
Object Detection (SP)
|
100% |
1304
103.4 IPS |
|
Object Detection (HP)
|
99% |
5874
467.2 IPS |
|
Object Detection (Q)
|
91% |
5058
404.2 IPS |
|
Face Detection (SP)
|
100% |
2515
29.9 IPS |
|
Face Detection (HP)
|
100% |
13851
164.6 IPS |
|
Face Detection (Q)
|
100% |
11723
139.3 IPS |
|
Depth Estimation (SP)
|
100% |
4650
35.8 IPS |
|
Depth Estimation (HP)
|
99% |
37252
287.0 IPS |
|
Depth Estimation (Q)
|
85% |
35457
277.1 IPS |
|
Style Transfer (SP)
|
100% |
12825
16.5 IPS |
|
Style Transfer (HP)
|
100% |
98310
126.4 IPS |
|
Style Transfer (Q)
|
96% |
96575
124.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
2767
102.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
18296
675.6 IPS |
|
Image Super-Resolution (Q)
|
99% |
22159
818.2 IPS |
|
Text Classification (SP)
|
100% |
2109
2.81 KIPS |
|
Text Classification (HP)
|
100% |
2197
2.93 KIPS |
|
Text Classification (Q)
|
93% |
2262
3.04 KIPS |
|
Machine Translation (SP)
|
100% |
2257
38.9 IPS |
|
Machine Translation (HP)
|
100% |
1936
33.3 IPS |
|
Machine Translation (Q)
|
98% |
1875
32.4 IPS |