User | M91 |
Upload Date | September 03 2024 11:31 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.1 |
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 | 7.51 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1640
304.9 IPS |
|
Image Classification (HP)
|
100% |
11059
2.06 KIPS |
|
Image Classification (Q)
|
99% |
13231
2.47 KIPS |
|
Image Segmentation (SP)
|
100% |
1619
26.2 IPS |
|
Image Segmentation (HP)
|
100% |
10453
169.5 IPS |
|
Image Segmentation (Q)
|
100% |
10529
170.7 IPS |
|
Pose Estimation (SP)
|
100% |
7612
8.88 IPS |
|
Pose Estimation (HP)
|
100% |
102321
119.4 IPS |
|
Pose Estimation (Q)
|
94% |
198349
232.7 IPS |
|
Object Detection (SP)
|
100% |
1782
141.4 IPS |
|
Object Detection (HP)
|
100% |
13109
1.04 KIPS |
|
Object Detection (Q)
|
91% |
18523
1.48 KIPS |
|
Face Detection (SP)
|
100% |
3212
38.2 IPS |
|
Face Detection (HP)
|
100% |
21824
259.3 IPS |
|
Face Detection (Q)
|
100% |
36975
439.3 IPS |
|
Depth Estimation (SP)
|
100% |
7086
54.6 IPS |
|
Depth Estimation (HP)
|
99% |
64769
499.0 IPS |
|
Depth Estimation (Q)
|
97% |
74450
575.7 IPS |
|
Style Transfer (SP)
|
100% |
20681
26.6 IPS |
|
Style Transfer (HP)
|
100% |
138934
178.6 IPS |
|
Style Transfer (Q)
|
100% |
139557
179.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
4817
177.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
34258
1.26 KIPS |
|
Image Super-Resolution (Q)
|
98% |
53728
1.99 KIPS |
|
Text Classification (SP)
|
100% |
3181
4.25 KIPS |
|
Text Classification (HP)
|
100% |
2766
3.69 KIPS |
|
Text Classification (Q)
|
93% |
1973
2.65 KIPS |
|
Machine Translation (SP)
|
100% |
3164
54.5 IPS |
|
Machine Translation (HP)
|
100% |
6208
106.9 IPS |
|
Machine Translation (Q)
|
98% |
7091
122.5 IPS |