| User | ju83 |
| Upload Date | November 06 2024 07:48 AM |
| Views | 13 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.1 |
| Model | iPhone XS |
| Model ID | iPhone11,2 |
| Motherboard | D321AP |
| CPU Information | |
|---|---|
| Name | Apple A12 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.49 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 3.69 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
354
65.9 IPS |
|
|
Image Classification (HP)
|
100% |
641
119.1 IPS |
|
|
Image Classification (Q)
|
96% |
533
99.5 IPS |
|
|
Image Segmentation (SP)
|
100% |
401
6.50 IPS |
|
|
Image Segmentation (HP)
|
100% |
693
11.2 IPS |
|
|
Image Segmentation (Q)
|
99% |
742
12.1 IPS |
|
|
Pose Estimation (SP)
|
100% |
1140
1.33 IPS |
|
|
Pose Estimation (HP)
|
100% |
1163
1.36 IPS |
|
|
Pose Estimation (Q)
|
96% |
998
1.17 IPS |
|
|
Object Detection (SP)
|
100% |
339
26.9 IPS |
|
|
Object Detection (HP)
|
99% |
657
52.1 IPS |
|
|
Object Detection (Q)
|
92% |
547
43.6 IPS |
|
|
Face Detection (SP)
|
100% |
801
9.52 IPS |
|
|
Face Detection (HP)
|
100% |
1652
19.6 IPS |
|
|
Face Detection (Q)
|
100% |
1125
13.4 IPS |
|
|
Depth Estimation (SP)
|
100% |
872
6.72 IPS |
|
|
Depth Estimation (HP)
|
98% |
1596
12.3 IPS |
|
|
Depth Estimation (Q)
|
85% |
1373
10.7 IPS |
|
|
Style Transfer (SP)
|
100% |
2199
2.83 IPS |
|
|
Style Transfer (HP)
|
100% |
3502
4.50 IPS |
|
|
Style Transfer (Q)
|
96% |
3457
4.46 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
637
23.5 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
868
32.1 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
648
23.9 IPS |
|
|
Text Classification (SP)
|
100% |
260
347.3 IPS |
|
|
Text Classification (HP)
|
100% |
556
741.9 IPS |
|
|
Text Classification (Q)
|
93% |
561
753.2 IPS |
|
|
Machine Translation (SP)
|
100% |
567
9.77 IPS |
|
|
Machine Translation (HP)
|
98% |
1036
17.9 IPS |
|
|
Machine Translation (Q)
|
98% |
993
17.2 IPS |