User | Kevin12356 |
Upload Date | November 12 2024 04:29 PM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A14 Bionic |
System Information | |
---|---|
Operating System | iOS 18.2 |
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% |
1183
220.0 IPS |
|
Image Classification (HP)
|
100% |
5120
952.2 IPS |
|
Image Classification (Q)
|
96% |
5044
942.0 IPS |
|
Image Segmentation (SP)
|
100% |
1131
18.3 IPS |
|
Image Segmentation (HP)
|
100% |
8772
142.2 IPS |
|
Image Segmentation (Q)
|
99% |
9147
148.3 IPS |
|
Pose Estimation (SP)
|
100% |
4310
5.03 IPS |
|
Pose Estimation (HP)
|
100% |
64523
75.3 IPS |
|
Pose Estimation (Q)
|
95% |
62097
72.8 IPS |
|
Object Detection (SP)
|
100% |
1241
98.4 IPS |
|
Object Detection (HP)
|
99% |
6118
486.7 IPS |
|
Object Detection (Q)
|
91% |
5655
451.8 IPS |
|
Face Detection (SP)
|
100% |
2445
29.1 IPS |
|
Face Detection (HP)
|
100% |
15161
180.1 IPS |
|
Face Detection (Q)
|
100% |
12536
149.0 IPS |
|
Depth Estimation (SP)
|
100% |
4426
34.1 IPS |
|
Depth Estimation (HP)
|
99% |
38796
298.9 IPS |
|
Depth Estimation (Q)
|
85% |
44224
345.6 IPS |
|
Style Transfer (SP)
|
100% |
11903
15.3 IPS |
|
Style Transfer (HP)
|
100% |
107454
138.1 IPS |
|
Style Transfer (Q)
|
96% |
103219
133.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
2496
92.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
17513
646.7 IPS |
|
Image Super-Resolution (Q)
|
99% |
18314
676.2 IPS |
|
Text Classification (SP)
|
100% |
2122
2.83 KIPS |
|
Text Classification (HP)
|
100% |
2308
3.08 KIPS |
|
Text Classification (Q)
|
93% |
2291
3.08 KIPS |
|
Machine Translation (SP)
|
100% |
2289
39.4 IPS |
|
Machine Translation (HP)
|
100% |
4340
74.8 IPS |
|
Machine Translation (Q)
|
98% |
4717
81.5 IPS |