Upload Date | January 04 2025 02:07 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A15 Bionic |
System Information | |
---|---|
Operating System | iOS 18.3 |
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% |
1336
248.4 IPS |
|
Image Classification (HP)
|
100% |
7838
1.46 KIPS |
|
Image Classification (Q)
|
96% |
8746
1.63 KIPS |
|
Image Segmentation (SP)
|
100% |
1283
20.8 IPS |
|
Image Segmentation (HP)
|
100% |
12080
195.8 IPS |
|
Image Segmentation (Q)
|
99% |
14007
227.1 IPS |
|
Pose Estimation (SP)
|
100% |
5536
6.46 IPS |
|
Pose Estimation (HP)
|
100% |
92927
108.4 IPS |
|
Pose Estimation (Q)
|
95% |
94438
110.7 IPS |
|
Object Detection (SP)
|
100% |
1402
111.2 IPS |
|
Object Detection (HP)
|
99% |
10849
863.0 IPS |
|
Object Detection (Q)
|
91% |
11368
908.3 IPS |
|
Face Detection (SP)
|
100% |
2625
31.2 IPS |
|
Face Detection (HP)
|
100% |
26735
317.7 IPS |
|
Face Detection (Q)
|
100% |
34926
415.0 IPS |
|
Depth Estimation (SP)
|
100% |
5355
41.3 IPS |
|
Depth Estimation (HP)
|
99% |
54068
416.6 IPS |
|
Depth Estimation (Q)
|
85% |
74058
578.7 IPS |
|
Style Transfer (SP)
|
100% |
16990
21.8 IPS |
|
Style Transfer (HP)
|
100% |
150378
193.3 IPS |
|
Style Transfer (Q)
|
96% |
160579
207.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
3831
141.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
26189
967.0 IPS |
|
Image Super-Resolution (Q)
|
99% |
29779
1.10 KIPS |
|
Text Classification (SP)
|
100% |
2455
3.28 KIPS |
|
Text Classification (HP)
|
100% |
2327
3.11 KIPS |
|
Text Classification (Q)
|
93% |
2494
3.35 KIPS |
|
Machine Translation (SP)
|
100% |
3481
60.0 IPS |
|
Machine Translation (HP)
|
100% |
6137
105.7 IPS |
|
Machine Translation (Q)
|
98% |
7237
125.1 IPS |