Upload Date | October 17 2024 03:12 PM |
Views | 2 |
System Information | |
---|---|
Operating System | iOS 16.7 |
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 |
L1 Instruction Cache | 128 KB x 1 |
L1 Data Cache | 64.0 KB x 1 |
L2 Cache | 4.00 MB x 1 |
Memory Information | |
---|---|
Size | 5.52 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
1692
316.7 IPS |
|
Image Classification (F16)
|
100% |
5805
1.09 KIPS |
|
Image Classification (I8)
|
99% |
5121
958.3 IPS |
|
Image Segmentation (F32)
|
100% |
592
9.89 IPS |
|
Image Segmentation (F16)
|
100% |
2990
49.9 IPS |
|
Image Segmentation (I8)
|
100% |
3049
50.9 IPS |
|
Pose Estimation (F32)
|
100% |
11140
13.5 IPS |
|
Pose Estimation (F16)
|
100% |
80091
97.0 IPS |
|
Pose Estimation (I8)
|
100% |
78705
95.3 IPS |
|
Object Detection (F32)
|
100% |
1482
110.6 IPS |
|
Object Detection (F16)
|
100% |
4388
327.6 IPS |
|
Object Detection (I8)
|
97% |
1526
113.9 IPS |
|
Face Detection (F32)
|
100% |
4561
54.2 IPS |
|
Face Detection (F16)
|
97% |
9334
111.0 IPS |
|
Face Detection (I8)
|
96% |
9657
114.8 IPS |
|
Depth Estimation (F32)
|
100% |
8721
67.6 IPS |
|
Depth Estimation (F16)
|
100% |
26335
204.2 IPS |
|
Depth Estimation (I8)
|
99% |
26747
207.4 IPS |
|
Style Transfer (F32)
|
100% |
18952
24.9 IPS |
|
Style Transfer (F16)
|
100% |
93595
123.1 IPS |
|
Style Transfer (I8)
|
100% |
91680
120.6 IPS |
|
Image Super-Resolution (F32)
|
100% |
4556
162.7 IPS |
|
Image Super-Resolution (F16)
|
100% |
12617
450.6 IPS |
|
Image Super-Resolution (I8)
|
100% |
11909
425.3 IPS |
|
Text Classification (F32)
|
100% |
426
612.5 IPS |
|
Text Classification (F16)
|
100% |
909
1.31 KIPS |
|
Text Classification (I8)
|
96% |
952
1.37 KIPS |
|
Machine Translation (F32)
|
100% |
909
16.7 IPS |
|
Machine Translation (F16)
|
100% |
1170
21.5 IPS |
|
Machine Translation (I8)
|
99% |
966
17.8 IPS |