User | ethanhsiao |
Upload Date | January 09 2025 03:46 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.2.1 |
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% |
1670
310.5 IPS |
|
Image Classification (HP)
|
100% |
11035
2.05 KIPS |
|
Image Classification (Q)
|
97% |
15378
2.87 KIPS |
|
Image Segmentation (SP)
|
100% |
1573
25.5 IPS |
|
Image Segmentation (HP)
|
100% |
15572
252.4 IPS |
|
Image Segmentation (Q)
|
99% |
20579
333.6 IPS |
|
Pose Estimation (SP)
|
100% |
7635
8.91 IPS |
|
Pose Estimation (HP)
|
100% |
104874
122.4 IPS |
|
Pose Estimation (Q)
|
95% |
203707
238.8 IPS |
|
Object Detection (SP)
|
100% |
1777
141.0 IPS |
|
Object Detection (HP)
|
100% |
13948
1.11 KIPS |
|
Object Detection (Q)
|
91% |
19074
1.52 KIPS |
|
Face Detection (SP)
|
100% |
3146
37.4 IPS |
|
Face Detection (HP)
|
100% |
33739
400.9 IPS |
|
Face Detection (Q)
|
100% |
50598
601.2 IPS |
|
Depth Estimation (SP)
|
100% |
6960
53.6 IPS |
|
Depth Estimation (HP)
|
99% |
78372
603.8 IPS |
|
Depth Estimation (Q)
|
85% |
128379
1.00 KIPS |
|
Style Transfer (SP)
|
100% |
20708
26.6 IPS |
|
Style Transfer (HP)
|
100% |
202794
260.7 IPS |
|
Style Transfer (Q)
|
96% |
247466
319.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
4898
180.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
33943
1.25 KIPS |
|
Image Super-Resolution (Q)
|
99% |
59629
2.20 KIPS |
|
Text Classification (SP)
|
100% |
3198
4.27 KIPS |
|
Text Classification (HP)
|
100% |
3168
4.23 KIPS |
|
Text Classification (Q)
|
93% |
2623
3.52 KIPS |
|
Machine Translation (SP)
|
100% |
3096
53.3 IPS |
|
Machine Translation (HP)
|
100% |
6202
106.8 IPS |
|
Machine Translation (Q)
|
98% |
7102
122.7 IPS |