User | astazyx |
Upload Date | September 06 2024 11:25 AM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A15 Bionic |
System Information | |
---|---|
Operating System | iOS 17.6.1 |
Model | iPhone 13 Pro |
Model ID | iPhone14,2 |
Motherboard | D63AP |
CPU Information | |
---|---|
Name | Apple A15 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.23 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 5.50 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1196
222.5 IPS |
|
Image Classification (HP)
|
100% |
4466
830.5 IPS |
|
Image Classification (Q)
|
96% |
4817
899.5 IPS |
|
Image Segmentation (SP)
|
100% |
668
10.8 IPS |
|
Image Segmentation (HP)
|
100% |
3955
64.1 IPS |
|
Image Segmentation (Q)
|
99% |
6195
100.4 IPS |
|
Pose Estimation (SP)
|
100% |
5782
6.75 IPS |
|
Pose Estimation (HP)
|
100% |
70676
82.5 IPS |
|
Pose Estimation (Q)
|
95% |
77812
91.2 IPS |
|
Object Detection (SP)
|
100% |
1213
96.2 IPS |
|
Object Detection (HP)
|
99% |
5445
433.1 IPS |
|
Object Detection (Q)
|
93% |
6572
524.4 IPS |
|
Face Detection (SP)
|
100% |
1913
22.7 IPS |
|
Face Detection (HP)
|
100% |
10892
129.4 IPS |
|
Face Detection (Q)
|
100% |
12281
145.9 IPS |
|
Depth Estimation (SP)
|
100% |
3743
28.8 IPS |
|
Depth Estimation (HP)
|
99% |
35148
270.8 IPS |
|
Depth Estimation (Q)
|
85% |
45720
357.3 IPS |
|
Style Transfer (SP)
|
100% |
10318
13.3 IPS |
|
Style Transfer (HP)
|
100% |
97596
125.5 IPS |
|
Style Transfer (Q)
|
95% |
88654
114.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
3124
115.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
13437
496.2 IPS |
|
Image Super-Resolution (Q)
|
99% |
15783
582.8 IPS |
|
Text Classification (SP)
|
100% |
1283
1.71 KIPS |
|
Text Classification (HP)
|
100% |
3007
4.01 KIPS |
|
Text Classification (Q)
|
93% |
2723
3.66 KIPS |
|
Machine Translation (SP)
|
100% |
1537
26.5 IPS |
|
Machine Translation (HP)
|
100% |
2117
36.5 IPS |
|
Machine Translation (Q)
|
98% |
2136
36.9 IPS |