Upload Date | December 22 2024 09:27 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.3 |
Model | iPhone 14 Pro |
Model ID | iPhone15,2 |
Motherboard | D73AP |
CPU Information | |
---|---|
Name | Apple A16 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.46 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 5.53 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1424
264.9 IPS |
|
Image Classification (HP)
|
100% |
9816
1.83 KIPS |
|
Image Classification (Q)
|
97% |
12480
2.33 KIPS |
|
Image Segmentation (SP)
|
100% |
1438
23.3 IPS |
|
Image Segmentation (HP)
|
100% |
15004
243.2 IPS |
|
Image Segmentation (Q)
|
99% |
18316
296.9 IPS |
|
Pose Estimation (SP)
|
100% |
7129
8.32 IPS |
|
Pose Estimation (HP)
|
100% |
97290
113.5 IPS |
|
Pose Estimation (Q)
|
95% |
101175
118.6 IPS |
|
Object Detection (SP)
|
100% |
1585
125.7 IPS |
|
Object Detection (HP)
|
100% |
12599
999.4 IPS |
|
Object Detection (Q)
|
91% |
14284
1.14 KIPS |
|
Face Detection (SP)
|
100% |
2835
33.7 IPS |
|
Face Detection (HP)
|
100% |
30876
366.9 IPS |
|
Face Detection (Q)
|
100% |
39223
466.1 IPS |
|
Depth Estimation (SP)
|
100% |
6135
47.3 IPS |
|
Depth Estimation (HP)
|
99% |
74479
573.8 IPS |
|
Depth Estimation (Q)
|
85% |
96247
752.5 IPS |
|
Style Transfer (SP)
|
100% |
19164
24.6 IPS |
|
Style Transfer (HP)
|
100% |
173028
222.4 IPS |
|
Style Transfer (Q)
|
96% |
170666
220.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
4236
156.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
31352
1.16 KIPS |
|
Image Super-Resolution (Q)
|
99% |
36549
1.35 KIPS |
|
Text Classification (SP)
|
100% |
2607
3.48 KIPS |
|
Text Classification (HP)
|
100% |
2251
3.00 KIPS |
|
Text Classification (Q)
|
93% |
2200
2.95 KIPS |
|
Machine Translation (SP)
|
100% |
3420
58.9 IPS |
|
Machine Translation (HP)
|
100% |
7344
126.5 IPS |
|
Machine Translation (Q)
|
98% |
8204
141.8 IPS |