User | Petenka315 |
Upload Date | August 17 2024 01:55 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A15 Bionic |
System Information | |
---|---|
Operating System | iOS 17.5.1 |
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% |
1165
216.7 IPS |
|
Image Classification (HP)
|
100% |
5305
986.6 IPS |
|
Image Classification (Q)
|
99% |
5961
1.11 KIPS |
|
Image Segmentation (SP)
|
100% |
647
10.5 IPS |
|
Image Segmentation (HP)
|
100% |
3801
61.6 IPS |
|
Image Segmentation (Q)
|
100% |
3897
63.2 IPS |
|
Pose Estimation (SP)
|
100% |
5703
6.65 IPS |
|
Pose Estimation (HP)
|
100% |
74619
87.1 IPS |
|
Pose Estimation (Q)
|
94% |
77015
90.3 IPS |
|
Object Detection (SP)
|
100% |
1229
97.4 IPS |
|
Object Detection (HP)
|
99% |
5507
438.1 IPS |
|
Object Detection (Q)
|
93% |
6600
526.6 IPS |
|
Face Detection (SP)
|
100% |
1911
22.7 IPS |
|
Face Detection (HP)
|
100% |
10543
125.3 IPS |
|
Face Detection (Q)
|
100% |
12264
145.7 IPS |
|
Depth Estimation (SP)
|
100% |
3789
29.2 IPS |
|
Depth Estimation (HP)
|
99% |
34508
265.9 IPS |
|
Depth Estimation (Q)
|
97% |
38986
301.4 IPS |
|
Style Transfer (SP)
|
100% |
10418
13.4 IPS |
|
Style Transfer (HP)
|
100% |
96353
123.9 IPS |
|
Style Transfer (Q)
|
100% |
97172
124.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
3172
117.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
13224
488.3 IPS |
|
Image Super-Resolution (Q)
|
98% |
14954
554.0 IPS |
|
Text Classification (SP)
|
100% |
1282
1.71 KIPS |
|
Text Classification (HP)
|
100% |
2603
3.47 KIPS |
|
Text Classification (Q)
|
93% |
2660
3.57 KIPS |
|
Machine Translation (SP)
|
100% |
1533
26.4 IPS |
|
Machine Translation (HP)
|
100% |
2203
37.9 IPS |
|
Machine Translation (Q)
|
98% |
2200
38.0 IPS |