| User | hermeschen1116 |
| Upload Date | October 04 2024 03:52 AM |
| Views | 3 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| 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% |
354
65.8 IPS |
|
|
Image Classification (HP)
|
100% |
340
63.2 IPS |
|
|
Image Classification (Q)
|
97% |
328
61.2 IPS |
|
|
Image Segmentation (SP)
|
100% |
1364
22.1 IPS |
|
|
Image Segmentation (HP)
|
100% |
1501
24.3 IPS |
|
|
Image Segmentation (Q)
|
99% |
1471
23.9 IPS |
|
|
Pose Estimation (SP)
|
100% |
6244
7.29 IPS |
|
|
Pose Estimation (HP)
|
100% |
8923
10.4 IPS |
|
|
Pose Estimation (Q)
|
95% |
7600
8.91 IPS |
|
|
Object Detection (SP)
|
100% |
653
51.8 IPS |
|
|
Object Detection (HP)
|
100% |
625
49.6 IPS |
|
|
Object Detection (Q)
|
91% |
602
48.1 IPS |
|
|
Face Detection (SP)
|
100% |
3320
39.5 IPS |
|
|
Face Detection (HP)
|
100% |
3234
38.4 IPS |
|
|
Face Detection (Q)
|
100% |
2555
30.4 IPS |
|
|
Depth Estimation (SP)
|
100% |
4020
31.0 IPS |
|
|
Depth Estimation (HP)
|
99% |
5405
41.6 IPS |
|
|
Depth Estimation (Q)
|
85% |
4743
37.1 IPS |
|
|
Style Transfer (SP)
|
100% |
12559
16.1 IPS |
|
|
Style Transfer (HP)
|
100% |
13468
17.3 IPS |
|
|
Style Transfer (Q)
|
96% |
12810
16.5 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1688
62.3 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1464
54.0 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1354
50.0 IPS |
|
|
Text Classification (SP)
|
100% |
2069
2.76 KIPS |
|
|
Text Classification (HP)
|
100% |
3554
4.74 KIPS |
|
|
Text Classification (Q)
|
93% |
3523
4.73 KIPS |
|
|
Machine Translation (SP)
|
100% |
268
4.62 IPS |
|
|
Machine Translation (HP)
|
100% |
262
4.52 IPS |
|
|
Machine Translation (Q)
|
98% |
270
4.67 IPS |