User | TSTR |
Upload Date | October 24 2024 09:42 AM |
Views | 5 |
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% |
1695
315.3 IPS |
|
Image Classification (HP)
|
100% |
11487
2.14 KIPS |
|
Image Classification (Q)
|
97% |
15017
2.80 KIPS |
|
Image Segmentation (SP)
|
100% |
1638
26.6 IPS |
|
Image Segmentation (HP)
|
100% |
15650
253.7 IPS |
|
Image Segmentation (Q)
|
99% |
20858
338.1 IPS |
|
Pose Estimation (SP)
|
100% |
8548
9.97 IPS |
|
Pose Estimation (HP)
|
100% |
106774
124.6 IPS |
|
Pose Estimation (Q)
|
95% |
204162
239.3 IPS |
|
Object Detection (SP)
|
100% |
1854
147.1 IPS |
|
Object Detection (HP)
|
100% |
13769
1.09 KIPS |
|
Object Detection (Q)
|
91% |
19123
1.53 KIPS |
|
Face Detection (SP)
|
100% |
3300
39.2 IPS |
|
Face Detection (HP)
|
100% |
34952
415.3 IPS |
|
Face Detection (Q)
|
100% |
49704
590.6 IPS |
|
Depth Estimation (SP)
|
100% |
7367
56.8 IPS |
|
Depth Estimation (HP)
|
99% |
78841
607.4 IPS |
|
Depth Estimation (Q)
|
85% |
126811
991.5 IPS |
|
Style Transfer (SP)
|
100% |
22167
28.5 IPS |
|
Style Transfer (HP)
|
100% |
203452
261.5 IPS |
|
Style Transfer (Q)
|
96% |
247602
319.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
5122
189.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
34821
1.29 KIPS |
|
Image Super-Resolution (Q)
|
99% |
55124
2.04 KIPS |
|
Text Classification (SP)
|
100% |
3191
4.26 KIPS |
|
Text Classification (HP)
|
100% |
2697
3.60 KIPS |
|
Text Classification (Q)
|
93% |
2880
3.87 KIPS |
|
Machine Translation (SP)
|
100% |
3153
54.3 IPS |
|
Machine Translation (HP)
|
100% |
6820
117.5 IPS |
|
Machine Translation (Q)
|
98% |
7508
129.8 IPS |