| Upload Date | October 19 2024 08:41 PM |
| Views | 14 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A14 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.0.1 |
| Model | iPhone 12 |
| Model ID | iPhone13,2 |
| Motherboard | D53gAP |
| 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 | 3.60 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1254
233.3 IPS |
|
|
Image Classification (HP)
|
100% |
1916
356.3 IPS |
|
|
Image Classification (Q)
|
96% |
1367
255.3 IPS |
|
|
Image Segmentation (SP)
|
100% |
1142
18.5 IPS |
|
|
Image Segmentation (HP)
|
100% |
1754
28.4 IPS |
|
|
Image Segmentation (Q)
|
99% |
2155
34.9 IPS |
|
|
Pose Estimation (SP)
|
100% |
5143
6.00 IPS |
|
|
Pose Estimation (HP)
|
100% |
10154
11.8 IPS |
|
|
Pose Estimation (Q)
|
95% |
9118
10.7 IPS |
|
|
Object Detection (SP)
|
100% |
1280
101.5 IPS |
|
|
Object Detection (HP)
|
97% |
2160
172.0 IPS |
|
|
Object Detection (Q)
|
94% |
1568
125.0 IPS |
|
|
Face Detection (SP)
|
100% |
2510
29.8 IPS |
|
|
Face Detection (HP)
|
100% |
4647
55.2 IPS |
|
|
Face Detection (Q)
|
100% |
2652
31.5 IPS |
|
|
Depth Estimation (SP)
|
100% |
4726
36.4 IPS |
|
|
Depth Estimation (HP)
|
98% |
9411
72.7 IPS |
|
|
Depth Estimation (Q)
|
85% |
6537
51.1 IPS |
|
|
Style Transfer (SP)
|
100% |
12880
16.6 IPS |
|
|
Style Transfer (HP)
|
100% |
21136
27.2 IPS |
|
|
Style Transfer (Q)
|
96% |
18160
23.4 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2750
101.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3979
146.9 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
3017
111.4 IPS |
|
|
Text Classification (SP)
|
100% |
2115
2.82 KIPS |
|
|
Text Classification (HP)
|
100% |
3578
4.78 KIPS |
|
|
Text Classification (Q)
|
93% |
3573
4.80 KIPS |
|
|
Machine Translation (SP)
|
100% |
2249
38.7 IPS |
|
|
Machine Translation (HP)
|
98% |
3259
56.3 IPS |
|
|
Machine Translation (Q)
|
98% |
3718
64.2 IPS |