User | RWR |
Upload Date | November 07 2024 09:46 PM |
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% |
1640
304.9 IPS |
|
Image Classification (HP)
|
100% |
11368
2.11 KIPS |
|
Image Classification (Q)
|
97% |
15102
2.82 KIPS |
|
Image Segmentation (SP)
|
100% |
1569
25.4 IPS |
|
Image Segmentation (HP)
|
100% |
15903
257.8 IPS |
|
Image Segmentation (Q)
|
99% |
20867
338.3 IPS |
|
Pose Estimation (SP)
|
100% |
7131
8.32 IPS |
|
Pose Estimation (HP)
|
100% |
100091
116.8 IPS |
|
Pose Estimation (Q)
|
95% |
202636
237.5 IPS |
|
Object Detection (SP)
|
100% |
1720
136.4 IPS |
|
Object Detection (HP)
|
100% |
13880
1.10 KIPS |
|
Object Detection (Q)
|
91% |
19123
1.53 KIPS |
|
Face Detection (SP)
|
100% |
3139
37.3 IPS |
|
Face Detection (HP)
|
100% |
35516
422.0 IPS |
|
Face Detection (Q)
|
100% |
51221
608.6 IPS |
|
Depth Estimation (SP)
|
100% |
6728
51.8 IPS |
|
Depth Estimation (HP)
|
99% |
78684
606.2 IPS |
|
Depth Estimation (Q)
|
85% |
128418
1.00 KIPS |
|
Style Transfer (SP)
|
100% |
19753
25.4 IPS |
|
Style Transfer (HP)
|
100% |
203429
261.5 IPS |
|
Style Transfer (Q)
|
96% |
247567
319.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
4598
169.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
33874
1.25 KIPS |
|
Image Super-Resolution (Q)
|
99% |
58138
2.15 KIPS |
|
Text Classification (SP)
|
100% |
3182
4.25 KIPS |
|
Text Classification (HP)
|
100% |
3241
4.33 KIPS |
|
Text Classification (Q)
|
93% |
2414
3.24 KIPS |
|
Machine Translation (SP)
|
100% |
3103
53.4 IPS |
|
Machine Translation (HP)
|
100% |
6177
106.4 IPS |
|
Machine Translation (Q)
|
98% |
7352
127.1 IPS |