User | danielmcfarland |
Upload Date | December 28 2024 09:54 PM |
Views | 9 |
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% |
2032
377.9 IPS |
|
Image Classification (HP)
|
100% |
15165
2.82 KIPS |
|
Image Classification (Q)
|
97% |
19672
3.67 KIPS |
|
Image Segmentation (SP)
|
100% |
1979
32.1 IPS |
|
Image Segmentation (HP)
|
100% |
18247
295.8 IPS |
|
Image Segmentation (Q)
|
99% |
24043
389.8 IPS |
|
Pose Estimation (SP)
|
100% |
9629
11.2 IPS |
|
Pose Estimation (HP)
|
100% |
154109
179.8 IPS |
|
Pose Estimation (Q)
|
95% |
294822
345.5 IPS |
|
Object Detection (SP)
|
100% |
2237
177.4 IPS |
|
Object Detection (HP)
|
100% |
16375
1.30 KIPS |
|
Object Detection (Q)
|
91% |
22400
1.79 KIPS |
|
Face Detection (SP)
|
100% |
3755
44.6 IPS |
|
Face Detection (HP)
|
100% |
41286
490.6 IPS |
|
Face Detection (Q)
|
100% |
57095
678.4 IPS |
|
Depth Estimation (SP)
|
100% |
8198
63.2 IPS |
|
Depth Estimation (HP)
|
99% |
95583
736.4 IPS |
|
Depth Estimation (Q)
|
85% |
160816
1.26 KIPS |
|
Style Transfer (SP)
|
100% |
25280
32.5 IPS |
|
Style Transfer (HP)
|
100% |
244561
314.4 IPS |
|
Style Transfer (Q)
|
96% |
301463
389.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
5924
218.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
52115
1.92 KIPS |
|
Image Super-Resolution (Q)
|
99% |
84579
3.12 KIPS |
|
Text Classification (SP)
|
100% |
3428
4.58 KIPS |
|
Text Classification (HP)
|
100% |
4374
5.84 KIPS |
|
Text Classification (Q)
|
93% |
4281
5.75 KIPS |
|
Machine Translation (SP)
|
100% |
3880
66.8 IPS |
|
Machine Translation (HP)
|
100% |
9332
160.8 IPS |
|
Machine Translation (Q)
|
98% |
11416
197.3 IPS |