Upload Date | September 18 2024 12:49 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.0 |
Model | iPhone 15 Pro Max |
Model ID | iPhone16,2 |
Motherboard | D84AP |
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 | 7.48 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1650
306.9 IPS |
|
Image Classification (HP)
|
100% |
10539
1.96 KIPS |
|
Image Classification (Q)
|
97% |
15208
2.84 KIPS |
|
Image Segmentation (SP)
|
100% |
1645
26.7 IPS |
|
Image Segmentation (HP)
|
100% |
12869
208.6 IPS |
|
Image Segmentation (Q)
|
99% |
15984
259.1 IPS |
|
Pose Estimation (SP)
|
100% |
7483
8.73 IPS |
|
Pose Estimation (HP)
|
100% |
101928
118.9 IPS |
|
Pose Estimation (Q)
|
95% |
203324
238.3 IPS |
|
Object Detection (SP)
|
100% |
1728
137.0 IPS |
|
Object Detection (HP)
|
100% |
13678
1.08 KIPS |
|
Object Detection (Q)
|
91% |
19194
1.53 KIPS |
|
Face Detection (SP)
|
100% |
3141
37.3 IPS |
|
Face Detection (HP)
|
100% |
34298
407.5 IPS |
|
Face Detection (Q)
|
100% |
49305
585.9 IPS |
|
Depth Estimation (SP)
|
100% |
6792
52.3 IPS |
|
Depth Estimation (HP)
|
99% |
78724
606.5 IPS |
|
Depth Estimation (Q)
|
85% |
128254
1.00 KIPS |
|
Style Transfer (SP)
|
100% |
19622
25.2 IPS |
|
Style Transfer (HP)
|
100% |
203348
261.4 IPS |
|
Style Transfer (Q)
|
96% |
245349
316.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
4621
170.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
34233
1.26 KIPS |
|
Image Super-Resolution (Q)
|
99% |
54763
2.02 KIPS |
|
Text Classification (SP)
|
100% |
3193
4.26 KIPS |
|
Text Classification (HP)
|
100% |
3152
4.21 KIPS |
|
Text Classification (Q)
|
93% |
3241
4.35 KIPS |
|
Machine Translation (SP)
|
100% |
3028
52.2 IPS |
|
Machine Translation (HP)
|
100% |
6184
106.5 IPS |
|
Machine Translation (Q)
|
98% |
7413
128.1 IPS |