User | WrigleyBeard |
Upload Date | December 12 2024 11:05 PM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A14 Bionic |
System Information | |
---|---|
Operating System | iOS 18.2 |
Model | iPhone 12 Pro Max |
Model ID | iPhone13,4 |
Motherboard | D54pAP |
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 | 5.56 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1264
235.0 IPS |
|
Image Classification (HP)
|
100% |
4688
871.9 IPS |
|
Image Classification (Q)
|
96% |
4668
871.8 IPS |
|
Image Segmentation (SP)
|
100% |
1139
18.5 IPS |
|
Image Segmentation (HP)
|
100% |
8415
136.4 IPS |
|
Image Segmentation (Q)
|
99% |
9006
146.0 IPS |
|
Pose Estimation (SP)
|
100% |
4931
5.75 IPS |
|
Pose Estimation (HP)
|
100% |
60217
70.3 IPS |
|
Pose Estimation (Q)
|
95% |
60748
71.2 IPS |
|
Object Detection (SP)
|
100% |
1289
102.3 IPS |
|
Object Detection (HP)
|
99% |
5873
467.2 IPS |
|
Object Detection (Q)
|
91% |
5008
400.2 IPS |
|
Face Detection (SP)
|
100% |
2506
29.8 IPS |
|
Face Detection (HP)
|
100% |
14276
169.6 IPS |
|
Face Detection (Q)
|
100% |
12254
145.6 IPS |
|
Depth Estimation (SP)
|
100% |
4498
34.7 IPS |
|
Depth Estimation (HP)
|
99% |
37458
288.6 IPS |
|
Depth Estimation (Q)
|
85% |
36281
283.5 IPS |
|
Style Transfer (SP)
|
100% |
12330
15.9 IPS |
|
Style Transfer (HP)
|
100% |
97004
124.7 IPS |
|
Style Transfer (Q)
|
96% |
99791
128.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
2562
94.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
18734
691.8 IPS |
|
Image Super-Resolution (Q)
|
99% |
18913
698.4 IPS |
|
Text Classification (SP)
|
100% |
2121
2.83 KIPS |
|
Text Classification (HP)
|
100% |
2133
2.85 KIPS |
|
Text Classification (Q)
|
93% |
2167
2.91 KIPS |
|
Machine Translation (SP)
|
100% |
2275
39.2 IPS |
|
Machine Translation (HP)
|
100% |
3382
58.3 IPS |
|
Machine Translation (Q)
|
98% |
4375
75.6 IPS |