Upload Date | September 18 2024 04:26 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.0 |
Model | iPhone 15 Pro Max |
Model ID | iPhone16,2 |
Motherboard | D84AP |
CPU Information | |
---|---|
Name | Apple A17 Pro |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.78 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.48 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1634
303.8 IPS |
|
Image Classification (HP)
|
100% |
12040
2.24 KIPS |
|
Image Classification (Q)
|
97% |
15111
2.82 KIPS |
|
Image Segmentation (SP)
|
100% |
1593
25.8 IPS |
|
Image Segmentation (HP)
|
100% |
12986
210.5 IPS |
|
Image Segmentation (Q)
|
99% |
15960
258.7 IPS |
|
Pose Estimation (SP)
|
100% |
7483
8.73 IPS |
|
Pose Estimation (HP)
|
100% |
106663
124.5 IPS |
|
Pose Estimation (Q)
|
95% |
204171
239.3 IPS |
|
Object Detection (SP)
|
100% |
1754
139.1 IPS |
|
Object Detection (HP)
|
100% |
13805
1.10 KIPS |
|
Object Detection (Q)
|
91% |
19309
1.54 KIPS |
|
Face Detection (SP)
|
100% |
3153
37.5 IPS |
|
Face Detection (HP)
|
100% |
33710
400.5 IPS |
|
Face Detection (Q)
|
100% |
49049
582.8 IPS |
|
Depth Estimation (SP)
|
100% |
7044
54.3 IPS |
|
Depth Estimation (HP)
|
99% |
78806
607.2 IPS |
|
Depth Estimation (Q)
|
85% |
129787
1.01 KIPS |
|
Style Transfer (SP)
|
100% |
20746
26.7 IPS |
|
Style Transfer (HP)
|
100% |
204596
263.0 IPS |
|
Style Transfer (Q)
|
96% |
247368
319.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
4853
179.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
34541
1.28 KIPS |
|
Image Super-Resolution (Q)
|
99% |
57490
2.12 KIPS |
|
Text Classification (SP)
|
100% |
3206
4.28 KIPS |
|
Text Classification (HP)
|
100% |
2893
3.86 KIPS |
|
Text Classification (Q)
|
93% |
1899
2.55 KIPS |
|
Machine Translation (SP)
|
100% |
3112
53.6 IPS |
|
Machine Translation (HP)
|
100% |
6199
106.8 IPS |
|
Machine Translation (Q)
|
98% |
7657
132.3 IPS |