User | winzee |
Upload Date | August 16 2024 11:22 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.0 |
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% |
1431
266.1 IPS |
|
Image Classification (HP)
|
100% |
9963
1.85 KIPS |
|
Image Classification (Q)
|
99% |
11776
2.20 KIPS |
|
Image Segmentation (SP)
|
100% |
1451
23.5 IPS |
|
Image Segmentation (HP)
|
100% |
10241
166.0 IPS |
|
Image Segmentation (Q)
|
100% |
10173
164.9 IPS |
|
Pose Estimation (SP)
|
100% |
6994
8.16 IPS |
|
Pose Estimation (HP)
|
100% |
91070
106.3 IPS |
|
Pose Estimation (Q)
|
94% |
97571
114.4 IPS |
|
Object Detection (SP)
|
100% |
1587
125.9 IPS |
|
Object Detection (HP)
|
100% |
11978
950.1 IPS |
|
Object Detection (Q)
|
91% |
14465
1.16 KIPS |
|
Face Detection (SP)
|
100% |
3017
35.8 IPS |
|
Face Detection (HP)
|
100% |
18652
221.6 IPS |
|
Face Detection (Q)
|
100% |
31033
368.7 IPS |
|
Depth Estimation (SP)
|
100% |
6254
48.2 IPS |
|
Depth Estimation (HP)
|
99% |
59603
459.2 IPS |
|
Depth Estimation (Q)
|
97% |
67312
520.5 IPS |
|
Style Transfer (SP)
|
100% |
18906
24.3 IPS |
|
Style Transfer (HP)
|
100% |
130359
167.6 IPS |
|
Style Transfer (Q)
|
100% |
132483
170.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
4205
155.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
31132
1.15 KIPS |
|
Image Super-Resolution (Q)
|
98% |
35592
1.32 KIPS |
|
Text Classification (SP)
|
100% |
2550
3.40 KIPS |
|
Text Classification (HP)
|
100% |
2088
2.79 KIPS |
|
Text Classification (Q)
|
93% |
2301
3.09 KIPS |
|
Machine Translation (SP)
|
100% |
3429
59.1 IPS |
|
Machine Translation (HP)
|
100% |
2376
40.9 IPS |
|
Machine Translation (Q)
|
98% |
2361
40.8 IPS |