| User | hermeschen1116 |
| Upload Date | October 04 2024 03:56 AM |
| Views | 15 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A14 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.1 |
| 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% |
1247
231.9 IPS |
|
|
Image Classification (HP)
|
100% |
4303
800.2 IPS |
|
|
Image Classification (Q)
|
96% |
4136
772.3 IPS |
|
|
Image Segmentation (SP)
|
100% |
1127
18.3 IPS |
|
|
Image Segmentation (HP)
|
100% |
8238
133.5 IPS |
|
|
Image Segmentation (Q)
|
99% |
8177
132.6 IPS |
|
|
Pose Estimation (SP)
|
100% |
4815
5.62 IPS |
|
|
Pose Estimation (HP)
|
100% |
61458
71.7 IPS |
|
|
Pose Estimation (Q)
|
95% |
61051
71.6 IPS |
|
|
Object Detection (SP)
|
100% |
1237
98.1 IPS |
|
|
Object Detection (HP)
|
99% |
5696
453.1 IPS |
|
|
Object Detection (Q)
|
91% |
5169
413.0 IPS |
|
|
Face Detection (SP)
|
100% |
2375
28.2 IPS |
|
|
Face Detection (HP)
|
100% |
13665
162.4 IPS |
|
|
Face Detection (Q)
|
100% |
11385
135.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
4628
35.7 IPS |
|
|
Depth Estimation (HP)
|
99% |
34614
266.7 IPS |
|
|
Depth Estimation (Q)
|
85% |
34391
268.7 IPS |
|
|
Style Transfer (SP)
|
100% |
11299
14.5 IPS |
|
|
Style Transfer (HP)
|
100% |
100274
128.9 IPS |
|
|
Style Transfer (Q)
|
96% |
99148
127.9 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2698
99.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
17446
644.2 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
19515
720.6 IPS |
|
|
Text Classification (SP)
|
100% |
2123
2.83 KIPS |
|
|
Text Classification (HP)
|
100% |
2375
3.17 KIPS |
|
|
Text Classification (Q)
|
93% |
2312
3.10 KIPS |
|
|
Machine Translation (SP)
|
100% |
2312
39.8 IPS |
|
|
Machine Translation (HP)
|
100% |
1825
31.4 IPS |
|
|
Machine Translation (Q)
|
98% |
1867
32.3 IPS |