User | TSTR |
Upload Date | March 05 2025 03:35 PM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 18.4 |
Model | iPhone 16 Pro |
Model ID | iPhone17,1 |
Motherboard | D93AP |
CPU Information | |
---|---|
Name | Apple A18 Pro |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 4.04 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.47 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2090
388.8 IPS |
|
Image Classification (HP)
|
100% |
14980
2.79 KIPS |
|
Image Classification (Q)
|
97% |
20068
3.75 KIPS |
|
Image Segmentation (SP)
|
100% |
2033
33.0 IPS |
|
Image Segmentation (HP)
|
100% |
18359
297.6 IPS |
|
Image Segmentation (Q)
|
99% |
24179
392.0 IPS |
|
Pose Estimation (SP)
|
100% |
9756
11.4 IPS |
|
Pose Estimation (HP)
|
100% |
154355
180.1 IPS |
|
Pose Estimation (Q)
|
95% |
294511
345.2 IPS |
|
Object Detection (SP)
|
100% |
2390
189.6 IPS |
|
Object Detection (HP)
|
100% |
16127
1.28 KIPS |
|
Object Detection (Q)
|
91% |
22783
1.82 KIPS |
|
Face Detection (SP)
|
100% |
4007
47.6 IPS |
|
Face Detection (HP)
|
100% |
40855
485.4 IPS |
|
Face Detection (Q)
|
100% |
56962
676.8 IPS |
|
Depth Estimation (SP)
|
100% |
8408
64.8 IPS |
|
Depth Estimation (HP)
|
99% |
95343
734.6 IPS |
|
Depth Estimation (Q)
|
85% |
161055
1.26 KIPS |
|
Style Transfer (SP)
|
100% |
21555
27.7 IPS |
|
Style Transfer (HP)
|
100% |
245129
315.1 IPS |
|
Style Transfer (Q)
|
96% |
299283
386.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
5871
216.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
51892
1.92 KIPS |
|
Image Super-Resolution (Q)
|
99% |
83322
3.08 KIPS |
|
Text Classification (SP)
|
100% |
3366
4.49 KIPS |
|
Text Classification (HP)
|
100% |
5096
6.80 KIPS |
|
Text Classification (Q)
|
93% |
4755
6.38 KIPS |
|
Machine Translation (SP)
|
100% |
4337
74.7 IPS |
|
Machine Translation (HP)
|
100% |
10106
174.1 IPS |
|
Machine Translation (Q)
|
98% |
10881
188.0 IPS |