Upload Date | January 05 2025 12:09 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.2 |
Model | iPhone 14 Pro Max |
Model ID | iPhone15,3 |
Motherboard | D74AP |
CPU Information | |
---|---|
Name | Apple A16 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.46 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 5.51 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1399
260.2 IPS |
|
Image Classification (HP)
|
100% |
10323
1.92 KIPS |
|
Image Classification (Q)
|
97% |
12176
2.27 KIPS |
|
Image Segmentation (SP)
|
100% |
1423
23.1 IPS |
|
Image Segmentation (HP)
|
100% |
14543
235.8 IPS |
|
Image Segmentation (Q)
|
99% |
18234
295.6 IPS |
|
Pose Estimation (SP)
|
100% |
7006
8.18 IPS |
|
Pose Estimation (HP)
|
100% |
94860
110.7 IPS |
|
Pose Estimation (Q)
|
95% |
101351
118.8 IPS |
|
Object Detection (SP)
|
100% |
1589
126.1 IPS |
|
Object Detection (HP)
|
100% |
12769
1.01 KIPS |
|
Object Detection (Q)
|
91% |
14554
1.16 KIPS |
|
Face Detection (SP)
|
100% |
3064
36.4 IPS |
|
Face Detection (HP)
|
100% |
28384
337.3 IPS |
|
Face Detection (Q)
|
100% |
38997
463.4 IPS |
|
Depth Estimation (SP)
|
100% |
6118
47.1 IPS |
|
Depth Estimation (HP)
|
99% |
75182
579.2 IPS |
|
Depth Estimation (Q)
|
85% |
96272
752.7 IPS |
|
Style Transfer (SP)
|
100% |
18820
24.2 IPS |
|
Style Transfer (HP)
|
100% |
164594
211.6 IPS |
|
Style Transfer (Q)
|
96% |
166512
214.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
4213
155.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
31692
1.17 KIPS |
|
Image Super-Resolution (Q)
|
99% |
35931
1.33 KIPS |
|
Text Classification (SP)
|
100% |
2614
3.49 KIPS |
|
Text Classification (HP)
|
100% |
2500
3.34 KIPS |
|
Text Classification (Q)
|
93% |
2299
3.09 KIPS |
|
Machine Translation (SP)
|
100% |
3455
59.5 IPS |
|
Machine Translation (HP)
|
100% |
7069
121.8 IPS |
|
Machine Translation (Q)
|
98% |
8152
140.9 IPS |