User | 1Dnepr |
Upload Date | April 06 2025 05:19 PM |
Views | 2 |
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% |
2085
387.8 IPS |
|
Image Classification (HP)
|
100% |
15162
2.82 KIPS |
|
Image Classification (Q)
|
97% |
20268
3.78 KIPS |
|
Image Segmentation (SP)
|
100% |
1980
32.1 IPS |
|
Image Segmentation (HP)
|
100% |
18326
297.1 IPS |
|
Image Segmentation (Q)
|
99% |
24286
393.7 IPS |
|
Pose Estimation (SP)
|
100% |
8945
10.4 IPS |
|
Pose Estimation (HP)
|
100% |
152073
177.4 IPS |
|
Pose Estimation (Q)
|
95% |
291625
341.8 IPS |
|
Object Detection (SP)
|
100% |
2333
185.1 IPS |
|
Object Detection (HP)
|
100% |
16131
1.28 KIPS |
|
Object Detection (Q)
|
91% |
22547
1.80 KIPS |
|
Face Detection (SP)
|
100% |
3954
47.0 IPS |
|
Face Detection (HP)
|
100% |
40332
479.2 IPS |
|
Face Detection (Q)
|
100% |
57640
684.9 IPS |
|
Depth Estimation (SP)
|
100% |
8173
63.0 IPS |
|
Depth Estimation (HP)
|
99% |
95144
733.0 IPS |
|
Depth Estimation (Q)
|
85% |
160606
1.26 KIPS |
|
Style Transfer (SP)
|
100% |
19982
25.7 IPS |
|
Style Transfer (HP)
|
100% |
243512
313.0 IPS |
|
Style Transfer (Q)
|
96% |
301877
389.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
5509
203.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
51001
1.88 KIPS |
|
Image Super-Resolution (Q)
|
99% |
83662
3.09 KIPS |
|
Text Classification (SP)
|
100% |
3368
4.50 KIPS |
|
Text Classification (HP)
|
100% |
4480
5.98 KIPS |
|
Text Classification (Q)
|
93% |
4429
5.94 KIPS |
|
Machine Translation (SP)
|
100% |
4287
73.8 IPS |
|
Machine Translation (HP)
|
100% |
10045
173.0 IPS |
|
Machine Translation (Q)
|
98% |
10925
188.8 IPS |