User | M91 |
Upload Date | August 26 2024 03:55 AM |
Views | 3 |
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% |
1737
323.0 IPS |
|
Image Classification (HP)
|
100% |
11130
2.07 KIPS |
|
Image Classification (Q)
|
99% |
13156
2.45 KIPS |
|
Image Segmentation (SP)
|
100% |
1669
27.1 IPS |
|
Image Segmentation (HP)
|
100% |
10569
171.3 IPS |
|
Image Segmentation (Q)
|
100% |
10534
170.8 IPS |
|
Pose Estimation (SP)
|
100% |
8393
9.79 IPS |
|
Pose Estimation (HP)
|
100% |
102949
120.1 IPS |
|
Pose Estimation (Q)
|
94% |
197364
231.5 IPS |
|
Object Detection (SP)
|
100% |
1830
145.1 IPS |
|
Object Detection (HP)
|
100% |
13135
1.04 KIPS |
|
Object Detection (Q)
|
91% |
18663
1.49 KIPS |
|
Face Detection (SP)
|
100% |
3284
39.0 IPS |
|
Face Detection (HP)
|
100% |
21793
258.9 IPS |
|
Face Detection (Q)
|
100% |
35432
421.0 IPS |
|
Depth Estimation (SP)
|
100% |
7224
55.7 IPS |
|
Depth Estimation (HP)
|
99% |
65048
501.2 IPS |
|
Depth Estimation (Q)
|
97% |
74218
573.9 IPS |
|
Style Transfer (SP)
|
100% |
21456
27.6 IPS |
|
Style Transfer (HP)
|
100% |
138677
178.3 IPS |
|
Style Transfer (Q)
|
100% |
139167
178.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
5061
186.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
34490
1.27 KIPS |
|
Image Super-Resolution (Q)
|
98% |
54148
2.01 KIPS |
|
Text Classification (SP)
|
100% |
3216
4.29 KIPS |
|
Text Classification (HP)
|
100% |
2784
3.72 KIPS |
|
Text Classification (Q)
|
93% |
1793
2.41 KIPS |
|
Machine Translation (SP)
|
100% |
3147
54.2 IPS |
|
Machine Translation (HP)
|
100% |
6138
105.7 IPS |
|
Machine Translation (Q)
|
98% |
7160
123.7 IPS |