User | Hogehoge |
Upload Date | September 01 2024 03:56 AM |
Views | 8 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.0 |
Model | iPhone 15 Pro |
Model ID | iPhone16,1 |
Motherboard | D83AP |
CPU Information | |
---|---|
Name | Apple A17 Pro |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.78 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.51 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1880
349.7 IPS |
|
Image Classification (HP)
|
100% |
1690
314.3 IPS |
|
Image Classification (Q)
|
99% |
2045
381.5 IPS |
|
Image Segmentation (SP)
|
100% |
3097
50.2 IPS |
|
Image Segmentation (HP)
|
100% |
3931
63.7 IPS |
|
Image Segmentation (Q)
|
100% |
3960
64.2 IPS |
|
Pose Estimation (SP)
|
100% |
15082
17.6 IPS |
|
Pose Estimation (HP)
|
100% |
15914
18.6 IPS |
|
Pose Estimation (Q)
|
97% |
14600
17.1 IPS |
|
Object Detection (SP)
|
100% |
2491
197.6 IPS |
|
Object Detection (HP)
|
100% |
3058
242.6 IPS |
|
Object Detection (Q)
|
91% |
2385
190.5 IPS |
|
Face Detection (SP)
|
100% |
6756
80.3 IPS |
|
Face Detection (HP)
|
100% |
9427
112.0 IPS |
|
Face Detection (Q)
|
100% |
6594
78.4 IPS |
|
Depth Estimation (SP)
|
100% |
12062
92.9 IPS |
|
Depth Estimation (HP)
|
99% |
13473
103.8 IPS |
|
Depth Estimation (Q)
|
97% |
1841
14.2 IPS |
|
Style Transfer (SP)
|
100% |
29285
37.6 IPS |
|
Style Transfer (HP)
|
100% |
34963
44.9 IPS |
|
Style Transfer (Q)
|
100% |
34480
44.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
6344
234.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
6672
246.4 IPS |
|
Image Super-Resolution (Q)
|
98% |
5137
190.3 IPS |
|
Text Classification (SP)
|
100% |
3248
4.33 KIPS |
|
Text Classification (HP)
|
100% |
5620
7.50 KIPS |
|
Text Classification (Q)
|
93% |
5503
7.39 KIPS |
|
Machine Translation (SP)
|
100% |
917
15.8 IPS |
|
Machine Translation (HP)
|
100% |
955
16.4 IPS |
|
Machine Translation (Q)
|
98% |
981
17.0 IPS |