User | sichunlam |
Upload Date | August 15 2024 09:13 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
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% |
1527
283.9 IPS |
|
Image Classification (HP)
|
100% |
2169
403.4 IPS |
|
Image Classification (Q)
|
99% |
2301
429.1 IPS |
|
Image Segmentation (SP)
|
100% |
3105
50.3 IPS |
|
Image Segmentation (HP)
|
100% |
3915
63.5 IPS |
|
Image Segmentation (Q)
|
100% |
3872
62.8 IPS |
|
Pose Estimation (SP)
|
100% |
15022
17.5 IPS |
|
Pose Estimation (HP)
|
100% |
15921
18.6 IPS |
|
Pose Estimation (Q)
|
96% |
14562
17.1 IPS |
|
Object Detection (SP)
|
100% |
2461
195.2 IPS |
|
Object Detection (HP)
|
100% |
2791
221.4 IPS |
|
Object Detection (Q)
|
92% |
2217
176.9 IPS |
|
Face Detection (SP)
|
100% |
6661
79.2 IPS |
|
Face Detection (HP)
|
100% |
8740
103.9 IPS |
|
Face Detection (Q)
|
100% |
5903
70.1 IPS |
|
Depth Estimation (SP)
|
100% |
12003
92.5 IPS |
|
Depth Estimation (HP)
|
99% |
12917
99.5 IPS |
|
Depth Estimation (Q)
|
97% |
13233
102.3 IPS |
|
Style Transfer (SP)
|
100% |
29756
38.3 IPS |
|
Style Transfer (HP)
|
100% |
35054
45.1 IPS |
|
Style Transfer (Q)
|
100% |
35134
45.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
6352
234.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
6655
245.7 IPS |
|
Image Super-Resolution (Q)
|
98% |
5503
203.9 IPS |
|
Text Classification (SP)
|
100% |
496
662.0 IPS |
|
Text Classification (HP)
|
100% |
525
700.1 IPS |
|
Text Classification (Q)
|
93% |
336
450.5 IPS |
|
Machine Translation (SP)
|
100% |
1206
20.8 IPS |
|
Machine Translation (HP)
|
100% |
1162
20.0 IPS |
|
Machine Translation (Q)
|
98% |
1567
27.1 IPS |