| User | anthonya1 |
| Upload Date | January 07 2025 04:13 AM |
| Views | 9 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A14 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.2 |
| Model | iPhone 12 Mini |
| Model ID | iPhone13,1 |
| Motherboard | D52gAP |
| 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 | 3.61 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1269
236.1 IPS |
|
|
Image Classification (HP)
|
100% |
1913
355.8 IPS |
|
|
Image Classification (Q)
|
96% |
1369
255.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
1143
18.5 IPS |
|
|
Image Segmentation (HP)
|
100% |
1761
28.5 IPS |
|
|
Image Segmentation (Q)
|
99% |
2163
35.1 IPS |
|
|
Pose Estimation (SP)
|
100% |
5088
5.94 IPS |
|
|
Pose Estimation (HP)
|
100% |
10115
11.8 IPS |
|
|
Pose Estimation (Q)
|
95% |
9037
10.6 IPS |
|
|
Object Detection (SP)
|
100% |
1288
102.2 IPS |
|
|
Object Detection (HP)
|
97% |
2164
172.3 IPS |
|
|
Object Detection (Q)
|
94% |
1554
123.8 IPS |
|
|
Face Detection (SP)
|
100% |
2541
30.2 IPS |
|
|
Face Detection (HP)
|
100% |
4697
55.8 IPS |
|
|
Face Detection (Q)
|
100% |
2629
31.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
4666
35.9 IPS |
|
|
Depth Estimation (HP)
|
98% |
9138
70.6 IPS |
|
|
Depth Estimation (Q)
|
85% |
6476
50.6 IPS |
|
|
Style Transfer (SP)
|
100% |
12748
16.4 IPS |
|
|
Style Transfer (HP)
|
100% |
20734
26.7 IPS |
|
|
Style Transfer (Q)
|
96% |
18128
23.4 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2747
101.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3890
143.6 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
2974
109.8 IPS |
|
|
Text Classification (SP)
|
100% |
2115
2.82 KIPS |
|
|
Text Classification (HP)
|
100% |
3636
4.85 KIPS |
|
|
Text Classification (Q)
|
93% |
3634
4.88 KIPS |
|
|
Machine Translation (SP)
|
100% |
2276
39.2 IPS |
|
|
Machine Translation (HP)
|
98% |
3319
57.3 IPS |
|
|
Machine Translation (Q)
|
98% |
3759
65.0 IPS |