| User | ote-sonic |
| Upload Date | September 27 2024 09:47 AM |
| Views | 19 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.1 |
| Model | iPhone XR |
| Model ID | iPhone11,8 |
| Motherboard | N841AP |
| 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 | 2.77 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
324
60.3 IPS |
|
|
Image Classification (HP)
|
100% |
549
102.0 IPS |
|
|
Image Classification (Q)
|
96% |
486
90.8 IPS |
|
|
Image Segmentation (SP)
|
100% |
367
5.95 IPS |
|
|
Image Segmentation (HP)
|
100% |
677
11.0 IPS |
|
|
Image Segmentation (Q)
|
99% |
723
11.7 IPS |
|
|
Pose Estimation (SP)
|
100% |
949
1.11 IPS |
|
|
Pose Estimation (HP)
|
100% |
936
1.09 IPS |
|
|
Pose Estimation (Q)
|
96% |
837
0.98 IPS |
|
|
Object Detection (SP)
|
100% |
283
22.5 IPS |
|
|
Object Detection (HP)
|
99% |
652
51.7 IPS |
|
|
Object Detection (Q)
|
92% |
468
37.3 IPS |
|
|
Face Detection (SP)
|
100% |
744
8.84 IPS |
|
|
Face Detection (HP)
|
100% |
1619
19.2 IPS |
|
|
Face Detection (Q)
|
100% |
994
11.8 IPS |
|
|
Depth Estimation (SP)
|
100% |
631
4.86 IPS |
|
|
Depth Estimation (HP)
|
98% |
1344
10.4 IPS |
|
|
Depth Estimation (Q)
|
85% |
1203
9.40 IPS |
|
|
Style Transfer (SP)
|
100% |
1820
2.34 IPS |
|
|
Style Transfer (HP)
|
100% |
3005
3.86 IPS |
|
|
Style Transfer (Q)
|
96% |
2722
3.51 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
494
18.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
711
26.3 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
693
25.6 IPS |
|
|
Text Classification (SP)
|
100% |
269
359.4 IPS |
|
|
Text Classification (HP)
|
100% |
551
735.1 IPS |
|
|
Text Classification (Q)
|
93% |
548
735.9 IPS |
|
|
Machine Translation (SP)
|
100% |
499
8.59 IPS |
|
|
Machine Translation (HP)
|
98% |
838
14.5 IPS |
|
|
Machine Translation (Q)
|
98% |
842
14.6 IPS |