| Upload Date | August 15 2024 03:49 AM |
| Views | 22 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A13 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 17.5.1 |
| Model | iPhone 11 Pro |
| Model ID | iPhone12,3 |
| Motherboard | D421AP |
| CPU Information | |
|---|---|
| Name | Apple A13 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.66 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 3.68 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
541
100.7 IPS |
|
|
Image Classification (HP)
|
100% |
2871
533.8 IPS |
|
|
Image Classification (Q)
|
99% |
2861
533.7 IPS |
|
|
Image Segmentation (SP)
|
100% |
444
7.20 IPS |
|
|
Image Segmentation (HP)
|
100% |
509
8.26 IPS |
|
|
Image Segmentation (Q)
|
100% |
507
8.22 IPS |
|
|
Pose Estimation (SP)
|
100% |
3317
3.87 IPS |
|
|
Pose Estimation (HP)
|
100% |
28677
33.5 IPS |
|
|
Pose Estimation (Q)
|
95% |
3381
3.96 IPS |
|
|
Object Detection (SP)
|
100% |
576
45.7 IPS |
|
|
Object Detection (HP)
|
100% |
2539
201.4 IPS |
|
|
Object Detection (Q)
|
94% |
295
23.5 IPS |
|
|
Face Detection (SP)
|
100% |
1115
13.2 IPS |
|
|
Face Detection (HP)
|
100% |
7129
84.7 IPS |
|
|
Face Detection (Q)
|
100% |
330
3.93 IPS |
|
|
Depth Estimation (SP)
|
100% |
1843
14.2 IPS |
|
|
Depth Estimation (HP)
|
99% |
23086
177.9 IPS |
|
|
Depth Estimation (Q)
|
97% |
23554
182.1 IPS |
|
|
Style Transfer (SP)
|
100% |
5266
6.77 IPS |
|
|
Style Transfer (HP)
|
100% |
11113
14.3 IPS |
|
|
Style Transfer (Q)
|
100% |
11173
14.4 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1662
61.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
4538
167.6 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
617
22.8 IPS |
|
|
Text Classification (SP)
|
100% |
736
982.2 IPS |
|
|
Text Classification (HP)
|
100% |
430
573.6 IPS |
|
|
Text Classification (Q)
|
93% |
429
576.2 IPS |
|
|
Machine Translation (SP)
|
100% |
788
13.6 IPS |
|
|
Machine Translation (HP)
|
100% |
986
17.0 IPS |
|
|
Machine Translation (Q)
|
98% |
1007
17.4 IPS |