User | M91 |
Upload Date | October 15 2024 10:45 AM |
Views | 4 |
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% |
1658
308.2 IPS |
|
Image Classification (HP)
|
100% |
10925
2.03 KIPS |
|
Image Classification (Q)
|
97% |
15574
2.91 KIPS |
|
Image Segmentation (SP)
|
100% |
1570
25.5 IPS |
|
Image Segmentation (HP)
|
100% |
16026
259.8 IPS |
|
Image Segmentation (Q)
|
99% |
20894
338.7 IPS |
|
Pose Estimation (SP)
|
100% |
6715
7.83 IPS |
|
Pose Estimation (HP)
|
100% |
99586
116.2 IPS |
|
Pose Estimation (Q)
|
95% |
202664
237.5 IPS |
|
Object Detection (SP)
|
100% |
1696
134.5 IPS |
|
Object Detection (HP)
|
100% |
13761
1.09 KIPS |
|
Object Detection (Q)
|
91% |
19107
1.53 KIPS |
|
Face Detection (SP)
|
100% |
3133
37.2 IPS |
|
Face Detection (HP)
|
100% |
34513
410.1 IPS |
|
Face Detection (Q)
|
100% |
51115
607.4 IPS |
|
Depth Estimation (SP)
|
100% |
6615
51.0 IPS |
|
Depth Estimation (HP)
|
99% |
78808
607.2 IPS |
|
Depth Estimation (Q)
|
85% |
128195
1.00 KIPS |
|
Style Transfer (SP)
|
100% |
18812
24.2 IPS |
|
Style Transfer (HP)
|
100% |
198186
254.8 IPS |
|
Style Transfer (Q)
|
96% |
247621
319.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
4370
161.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
34187
1.26 KIPS |
|
Image Super-Resolution (Q)
|
99% |
59681
2.20 KIPS |
|
Text Classification (SP)
|
100% |
3174
4.24 KIPS |
|
Text Classification (HP)
|
100% |
3111
4.15 KIPS |
|
Text Classification (Q)
|
93% |
3175
4.26 KIPS |
|
Machine Translation (SP)
|
100% |
3136
54.0 IPS |
|
Machine Translation (HP)
|
100% |
6288
108.3 IPS |
|
Machine Translation (Q)
|
98% |
7749
133.9 IPS |