| User | MPN196 |
| Upload Date | August 16 2024 03:08 PM |
| Views | 5 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A14 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| 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 | 5.52 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
935
173.8 IPS |
|
|
Image Classification (HP)
|
100% |
4320
803.4 IPS |
|
|
Image Classification (Q)
|
99% |
4838
902.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
591
9.57 IPS |
|
|
Image Segmentation (HP)
|
100% |
3519
57.0 IPS |
|
|
Image Segmentation (Q)
|
100% |
3588
58.2 IPS |
|
|
Pose Estimation (SP)
|
100% |
4888
5.70 IPS |
|
|
Pose Estimation (HP)
|
100% |
57396
67.0 IPS |
|
|
Pose Estimation (Q)
|
94% |
58300
68.4 IPS |
|
|
Object Detection (SP)
|
100% |
996
79.0 IPS |
|
|
Object Detection (HP)
|
99% |
5251
417.7 IPS |
|
|
Object Detection (Q)
|
93% |
4837
385.9 IPS |
|
|
Face Detection (SP)
|
100% |
1638
19.5 IPS |
|
|
Face Detection (HP)
|
100% |
11208
133.2 IPS |
|
|
Face Detection (Q)
|
100% |
10634
126.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
3257
25.1 IPS |
|
|
Depth Estimation (HP)
|
99% |
33221
255.9 IPS |
|
|
Depth Estimation (Q)
|
97% |
36655
283.4 IPS |
|
|
Style Transfer (SP)
|
100% |
8759
11.3 IPS |
|
|
Style Transfer (HP)
|
100% |
96281
123.8 IPS |
|
|
Style Transfer (Q)
|
100% |
98693
126.9 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2301
84.9 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
13708
506.2 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
16764
621.1 IPS |
|
|
Text Classification (SP)
|
100% |
1142
1.52 KIPS |
|
|
Text Classification (HP)
|
100% |
3099
4.14 KIPS |
|
|
Text Classification (Q)
|
93% |
2607
3.50 KIPS |
|
|
Machine Translation (SP)
|
100% |
1143
19.7 IPS |
|
|
Machine Translation (HP)
|
100% |
1909
32.9 IPS |
|
|
Machine Translation (Q)
|
98% |
1940
33.5 IPS |