User | Hogehoge |
Upload Date | September 09 2024 11:46 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 17.6.1 |
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 | 7.47 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1402
260.7 IPS |
|
Image Classification (HP)
|
100% |
6186
1.15 KIPS |
|
Image Classification (Q)
|
97% |
7188
1.34 KIPS |
|
Image Segmentation (SP)
|
100% |
776
12.6 IPS |
|
Image Segmentation (HP)
|
100% |
5212
84.5 IPS |
|
Image Segmentation (Q)
|
99% |
10021
162.4 IPS |
|
Pose Estimation (SP)
|
100% |
6836
7.98 IPS |
|
Pose Estimation (HP)
|
100% |
86838
101.3 IPS |
|
Pose Estimation (Q)
|
95% |
152902
179.2 IPS |
|
Object Detection (SP)
|
100% |
1426
113.1 IPS |
|
Object Detection (HP)
|
100% |
8027
636.7 IPS |
|
Object Detection (Q)
|
93% |
9979
796.2 IPS |
|
Face Detection (SP)
|
100% |
2178
25.9 IPS |
|
Face Detection (HP)
|
100% |
11201
133.1 IPS |
|
Face Detection (Q)
|
100% |
13268
157.7 IPS |
|
Depth Estimation (SP)
|
100% |
4542
35.0 IPS |
|
Depth Estimation (HP)
|
99% |
42257
325.6 IPS |
|
Depth Estimation (Q)
|
85% |
58291
455.7 IPS |
|
Style Transfer (SP)
|
100% |
12113
15.6 IPS |
|
Style Transfer (HP)
|
100% |
128456
165.1 IPS |
|
Style Transfer (Q)
|
96% |
138155
178.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
3986
147.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
18743
692.1 IPS |
|
Image Super-Resolution (Q)
|
99% |
26727
986.9 IPS |
|
Text Classification (SP)
|
100% |
1807
2.41 KIPS |
|
Text Classification (HP)
|
71% |
4907
7.06 KIPS |
|
Text Classification (Q)
|
69% |
4961
7.27 KIPS |
|
Machine Translation (SP)
|
100% |
1893
32.6 IPS |
|
Machine Translation (HP)
|
100% |
2542
43.8 IPS |
|
Machine Translation (Q)
|
98% |
2534
43.8 IPS |