User | Ricochet |
Upload Date | September 02 2024 06:42 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% |
1473
273.9 IPS |
|
Image Classification (HP)
|
100% |
6286
1.17 KIPS |
|
Image Classification (Q)
|
99% |
6766
1.26 KIPS |
|
Image Segmentation (SP)
|
100% |
806
13.1 IPS |
|
Image Segmentation (HP)
|
100% |
5218
84.6 IPS |
|
Image Segmentation (Q)
|
100% |
5254
85.2 IPS |
|
Pose Estimation (SP)
|
100% |
7693
8.98 IPS |
|
Pose Estimation (HP)
|
100% |
87373
101.9 IPS |
|
Pose Estimation (Q)
|
94% |
150067
176.0 IPS |
|
Object Detection (SP)
|
100% |
1500
119.0 IPS |
|
Object Detection (HP)
|
100% |
8190
649.6 IPS |
|
Object Detection (Q)
|
93% |
9925
792.0 IPS |
|
Face Detection (SP)
|
100% |
2279
27.1 IPS |
|
Face Detection (HP)
|
100% |
11169
132.7 IPS |
|
Face Detection (Q)
|
100% |
13257
157.5 IPS |
|
Depth Estimation (SP)
|
100% |
4741
36.5 IPS |
|
Depth Estimation (HP)
|
99% |
42368
326.4 IPS |
|
Depth Estimation (Q)
|
97% |
47749
369.2 IPS |
|
Style Transfer (SP)
|
100% |
12319
15.8 IPS |
|
Style Transfer (HP)
|
100% |
127679
164.1 IPS |
|
Style Transfer (Q)
|
100% |
128325
165.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
4153
153.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
18276
674.8 IPS |
|
Image Super-Resolution (Q)
|
98% |
26278
973.6 IPS |
|
Text Classification (SP)
|
100% |
1787
2.39 KIPS |
|
Text Classification (HP)
|
71% |
4867
7.00 KIPS |
|
Text Classification (Q)
|
69% |
4724
6.93 KIPS |
|
Machine Translation (SP)
|
100% |
1898
32.7 IPS |
|
Machine Translation (HP)
|
100% |
2564
44.2 IPS |
|
Machine Translation (Q)
|
98% |
2556
44.2 IPS |