User | M91 |
Upload Date | April 01 2025 03:19 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.4 |
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 | 7.50 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1709
317.8 IPS |
|
Image Classification (HP)
|
100% |
11326
2.11 KIPS |
|
Image Classification (Q)
|
97% |
15553
2.90 KIPS |
|
Image Segmentation (SP)
|
100% |
1660
26.9 IPS |
|
Image Segmentation (HP)
|
100% |
16048
260.1 IPS |
|
Image Segmentation (Q)
|
99% |
21395
346.8 IPS |
|
Pose Estimation (SP)
|
100% |
7321
8.54 IPS |
|
Pose Estimation (HP)
|
100% |
105463
123.1 IPS |
|
Pose Estimation (Q)
|
95% |
204399
239.6 IPS |
|
Object Detection (SP)
|
100% |
1763
139.9 IPS |
|
Object Detection (HP)
|
100% |
13881
1.10 KIPS |
|
Object Detection (Q)
|
91% |
19437
1.55 KIPS |
|
Face Detection (SP)
|
100% |
3146
37.4 IPS |
|
Face Detection (HP)
|
100% |
33894
402.7 IPS |
|
Face Detection (Q)
|
100% |
51795
615.4 IPS |
|
Depth Estimation (SP)
|
100% |
6756
52.0 IPS |
|
Depth Estimation (HP)
|
99% |
78396
604.0 IPS |
|
Depth Estimation (Q)
|
85% |
128160
1.00 KIPS |
|
Style Transfer (SP)
|
100% |
20174
25.9 IPS |
|
Style Transfer (HP)
|
100% |
207514
266.8 IPS |
|
Style Transfer (Q)
|
96% |
256320
330.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
4628
170.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
33692
1.24 KIPS |
|
Image Super-Resolution (Q)
|
99% |
60909
2.25 KIPS |
|
Text Classification (SP)
|
100% |
3236
4.32 KIPS |
|
Text Classification (HP)
|
100% |
3480
4.64 KIPS |
|
Text Classification (Q)
|
93% |
2994
4.02 KIPS |
|
Machine Translation (SP)
|
100% |
3219
55.4 IPS |
|
Machine Translation (HP)
|
100% |
6634
114.3 IPS |
|
Machine Translation (Q)
|
98% |
7495
129.5 IPS |