Upload Date | October 04 2024 08:24 PM |
Views | 2 |
System Information | |
---|---|
Operating System | iOS 18.0 |
Model | iPhone17,2 |
Model ID | iPhone17,2 |
Motherboard | D94AP |
CPU Information | |
---|---|
Name | ARM |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 4.03 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 | 7.47 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
1255
234.8 IPS |
|
Image Classification (F16)
|
100% |
12938
2.42 KIPS |
|
Image Classification (I8)
|
99% |
14860
2.78 KIPS |
|
Image Segmentation (F32)
|
100% |
1543
25.8 IPS |
|
Image Segmentation (F16)
|
100% |
2730
45.6 IPS |
|
Image Segmentation (I8)
|
100% |
2563
42.8 IPS |
|
Pose Estimation (F32)
|
100% |
15126
18.3 IPS |
|
Pose Estimation (F16)
|
100% |
136104
164.8 IPS |
|
Pose Estimation (I8)
|
100% |
140542
170.2 IPS |
|
Object Detection (F32)
|
100% |
1385
103.4 IPS |
|
Object Detection (F16)
|
100% |
6107
455.9 IPS |
|
Object Detection (I8)
|
97% |
1486
110.9 IPS |
|
Face Detection (F32)
|
100% |
6873
81.7 IPS |
|
Face Detection (F16)
|
97% |
21599
256.8 IPS |
|
Face Detection (I8)
|
96% |
22022
261.8 IPS |
|
Depth Estimation (F32)
|
100% |
13694
106.2 IPS |
|
Depth Estimation (F16)
|
100% |
63377
491.5 IPS |
|
Depth Estimation (I8)
|
37% |
57713
447.6 IPS |
|
Style Transfer (F32)
|
100% |
32104
42.2 IPS |
|
Style Transfer (F16)
|
100% |
150797
198.4 IPS |
|
Style Transfer (I8)
|
100% |
150813
198.4 IPS |
|
Image Super-Resolution (F32)
|
100% |
7429
265.3 IPS |
|
Image Super-Resolution (F16)
|
100% |
45807
1.64 KIPS |
|
Image Super-Resolution (I8)
|
100% |
44351
1.58 KIPS |
|
Text Classification (F32)
|
100% |
3226
4.64 KIPS |
|
Text Classification (F16)
|
100% |
5400
7.76 KIPS |
|
Text Classification (I8)
|
96% |
5417
7.79 KIPS |
|
Machine Translation (F32)
|
100% |
601
11.1 IPS |
|
Machine Translation (F16)
|
100% |
1694
31.2 IPS |
|
Machine Translation (I8)
|
99% |
651
12.0 IPS |