Upload Date | January 07 2025 05:21 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.2.1 |
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% |
1394
259.3 IPS |
|
Image Classification (HP)
|
100% |
9846
1.83 KIPS |
|
Image Classification (Q)
|
97% |
12184
2.27 KIPS |
|
Image Segmentation (SP)
|
100% |
1497
24.3 IPS |
|
Image Segmentation (HP)
|
100% |
14909
241.7 IPS |
|
Image Segmentation (Q)
|
99% |
18605
301.6 IPS |
|
Pose Estimation (SP)
|
100% |
7036
8.21 IPS |
|
Pose Estimation (HP)
|
100% |
97378
113.6 IPS |
|
Pose Estimation (Q)
|
95% |
101677
119.2 IPS |
|
Object Detection (SP)
|
100% |
1594
126.5 IPS |
|
Object Detection (HP)
|
100% |
12783
1.01 KIPS |
|
Object Detection (Q)
|
91% |
14750
1.18 KIPS |
|
Face Detection (SP)
|
100% |
3085
36.7 IPS |
|
Face Detection (HP)
|
100% |
31216
370.9 IPS |
|
Face Detection (Q)
|
100% |
40316
479.0 IPS |
|
Depth Estimation (SP)
|
100% |
6271
48.3 IPS |
|
Depth Estimation (HP)
|
99% |
73968
569.9 IPS |
|
Depth Estimation (Q)
|
85% |
95918
749.9 IPS |
|
Style Transfer (SP)
|
100% |
18998
24.4 IPS |
|
Style Transfer (HP)
|
100% |
175036
225.0 IPS |
|
Style Transfer (Q)
|
96% |
175104
226.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
4319
159.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
32958
1.22 KIPS |
|
Image Super-Resolution (Q)
|
99% |
37653
1.39 KIPS |
|
Text Classification (SP)
|
100% |
2669
3.56 KIPS |
|
Text Classification (HP)
|
100% |
2872
3.83 KIPS |
|
Text Classification (Q)
|
93% |
2613
3.51 KIPS |
|
Machine Translation (SP)
|
100% |
3644
62.8 IPS |
|
Machine Translation (HP)
|
100% |
7158
123.3 IPS |
|
Machine Translation (Q)
|
98% |
8018
138.6 IPS |