User | danielmcfarland |
Upload Date | December 27 2024 03:39 PM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 18.2 |
Model | iPhone 16 Pro |
Model ID | iPhone17,1 |
Motherboard | D93AP |
CPU Information | |
---|---|
Name | Apple A18 Pro |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 4.04 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.48 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2000
372.0 IPS |
|
Image Classification (HP)
|
100% |
15300
2.85 KIPS |
|
Image Classification (Q)
|
97% |
20439
3.81 KIPS |
|
Image Segmentation (SP)
|
100% |
1936
31.4 IPS |
|
Image Segmentation (HP)
|
100% |
18396
298.2 IPS |
|
Image Segmentation (Q)
|
99% |
24107
390.8 IPS |
|
Pose Estimation (SP)
|
100% |
8053
9.40 IPS |
|
Pose Estimation (HP)
|
100% |
145267
169.5 IPS |
|
Pose Estimation (Q)
|
95% |
293145
343.6 IPS |
|
Object Detection (SP)
|
100% |
2079
164.9 IPS |
|
Object Detection (HP)
|
100% |
16294
1.29 KIPS |
|
Object Detection (Q)
|
91% |
22624
1.81 KIPS |
|
Face Detection (SP)
|
100% |
3450
41.0 IPS |
|
Face Detection (HP)
|
100% |
40724
483.9 IPS |
|
Face Detection (Q)
|
100% |
57545
683.8 IPS |
|
Depth Estimation (SP)
|
100% |
7089
54.6 IPS |
|
Depth Estimation (HP)
|
99% |
95051
732.3 IPS |
|
Depth Estimation (Q)
|
85% |
165510
1.29 KIPS |
|
Style Transfer (SP)
|
100% |
22588
29.0 IPS |
|
Style Transfer (HP)
|
100% |
245438
315.5 IPS |
|
Style Transfer (Q)
|
96% |
300648
388.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
5421
200.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
50246
1.86 KIPS |
|
Image Super-Resolution (Q)
|
99% |
84191
3.11 KIPS |
|
Text Classification (SP)
|
100% |
3427
4.57 KIPS |
|
Text Classification (HP)
|
100% |
4836
6.45 KIPS |
|
Text Classification (Q)
|
93% |
4884
6.56 KIPS |
|
Machine Translation (SP)
|
100% |
3824
65.9 IPS |
|
Machine Translation (HP)
|
100% |
9852
169.7 IPS |
|
Machine Translation (Q)
|
98% |
11403
197.1 IPS |