Upload Date | November 21 2024 06:54 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A15 Bionic |
System Information | |
---|---|
Operating System | iOS 18.1.1 |
Model | iPhone 13 Pro Max |
Model ID | iPhone14,3 |
Motherboard | D64AP |
CPU Information | |
---|---|
Name | Apple A15 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.23 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 5.51 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1345
250.1 IPS |
|
Image Classification (HP)
|
100% |
9203
1.71 KIPS |
|
Image Classification (Q)
|
96% |
10984
2.05 KIPS |
|
Image Segmentation (SP)
|
100% |
1306
21.2 IPS |
|
Image Segmentation (HP)
|
100% |
12846
208.2 IPS |
|
Image Segmentation (Q)
|
99% |
14833
240.5 IPS |
|
Pose Estimation (SP)
|
100% |
6127
7.15 IPS |
|
Pose Estimation (HP)
|
100% |
92748
108.2 IPS |
|
Pose Estimation (Q)
|
95% |
93001
109.0 IPS |
|
Object Detection (SP)
|
100% |
1462
116.0 IPS |
|
Object Detection (HP)
|
99% |
10688
850.2 IPS |
|
Object Detection (Q)
|
91% |
11263
899.9 IPS |
|
Face Detection (SP)
|
100% |
2729
32.4 IPS |
|
Face Detection (HP)
|
100% |
28484
338.4 IPS |
|
Face Detection (Q)
|
100% |
32851
390.3 IPS |
|
Depth Estimation (SP)
|
100% |
5553
42.8 IPS |
|
Depth Estimation (HP)
|
99% |
53105
409.1 IPS |
|
Depth Estimation (Q)
|
85% |
70941
554.4 IPS |
|
Style Transfer (SP)
|
100% |
17684
22.7 IPS |
|
Style Transfer (HP)
|
100% |
156705
201.4 IPS |
|
Style Transfer (Q)
|
96% |
153188
197.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
3954
146.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
26470
977.4 IPS |
|
Image Super-Resolution (Q)
|
99% |
28865
1.07 KIPS |
|
Text Classification (SP)
|
100% |
2416
3.23 KIPS |
|
Text Classification (HP)
|
100% |
2346
3.13 KIPS |
|
Text Classification (Q)
|
93% |
2388
3.21 KIPS |
|
Machine Translation (SP)
|
100% |
3391
58.4 IPS |
|
Machine Translation (HP)
|
100% |
4692
80.8 IPS |
|
Machine Translation (Q)
|
98% |
5195
89.8 IPS |