Upload Date | September 18 2024 10:26 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% |
1703
316.6 IPS |
|
Image Classification (HP)
|
100% |
11236
2.09 KIPS |
|
Image Classification (Q)
|
97% |
16172
3.02 KIPS |
|
Image Segmentation (SP)
|
100% |
1613
26.1 IPS |
|
Image Segmentation (HP)
|
100% |
12912
209.3 IPS |
|
Image Segmentation (Q)
|
99% |
15834
256.7 IPS |
|
Pose Estimation (SP)
|
100% |
8323
9.71 IPS |
|
Pose Estimation (HP)
|
100% |
106841
124.7 IPS |
|
Pose Estimation (Q)
|
95% |
205214
240.5 IPS |
|
Object Detection (SP)
|
100% |
1795
142.4 IPS |
|
Object Detection (HP)
|
100% |
13640
1.08 KIPS |
|
Object Detection (Q)
|
91% |
20266
1.62 KIPS |
|
Face Detection (SP)
|
100% |
3085
36.7 IPS |
|
Face Detection (HP)
|
100% |
33466
397.6 IPS |
|
Face Detection (Q)
|
100% |
48922
581.3 IPS |
|
Depth Estimation (SP)
|
100% |
7150
55.1 IPS |
|
Depth Estimation (HP)
|
99% |
78761
606.8 IPS |
|
Depth Estimation (Q)
|
85% |
127563
997.3 IPS |
|
Style Transfer (SP)
|
100% |
21273
27.3 IPS |
|
Style Transfer (HP)
|
100% |
203406
261.5 IPS |
|
Style Transfer (Q)
|
96% |
246675
318.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
5037
186.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
34484
1.27 KIPS |
|
Image Super-Resolution (Q)
|
99% |
57933
2.14 KIPS |
|
Text Classification (SP)
|
100% |
3183
4.25 KIPS |
|
Text Classification (HP)
|
100% |
3129
4.18 KIPS |
|
Text Classification (Q)
|
93% |
3167
4.25 KIPS |
|
Machine Translation (SP)
|
100% |
3115
53.7 IPS |
|
Machine Translation (HP)
|
100% |
6102
105.1 IPS |
|
Machine Translation (Q)
|
98% |
7745
133.8 IPS |