Upload Date | October 13 2024 11:30 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.0.1 |
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% |
1688
314.0 IPS |
|
Image Classification (HP)
|
100% |
11226
2.09 KIPS |
|
Image Classification (Q)
|
97% |
15545
2.90 KIPS |
|
Image Segmentation (SP)
|
100% |
1544
25.0 IPS |
|
Image Segmentation (HP)
|
100% |
12908
209.2 IPS |
|
Image Segmentation (Q)
|
99% |
15957
258.7 IPS |
|
Pose Estimation (SP)
|
100% |
7474
8.72 IPS |
|
Pose Estimation (HP)
|
100% |
105196
122.7 IPS |
|
Pose Estimation (Q)
|
95% |
202763
237.7 IPS |
|
Object Detection (SP)
|
100% |
1738
137.9 IPS |
|
Object Detection (HP)
|
100% |
13542
1.07 KIPS |
|
Object Detection (Q)
|
91% |
19085
1.52 KIPS |
|
Face Detection (SP)
|
100% |
3110
37.0 IPS |
|
Face Detection (HP)
|
100% |
34414
408.9 IPS |
|
Face Detection (Q)
|
100% |
50576
601.0 IPS |
|
Depth Estimation (SP)
|
100% |
6883
53.0 IPS |
|
Depth Estimation (HP)
|
99% |
78359
603.7 IPS |
|
Depth Estimation (Q)
|
85% |
127901
1000.0 IPS |
|
Style Transfer (SP)
|
100% |
20209
26.0 IPS |
|
Style Transfer (HP)
|
100% |
204072
262.3 IPS |
|
Style Transfer (Q)
|
96% |
248073
320.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
4720
174.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
34214
1.26 KIPS |
|
Image Super-Resolution (Q)
|
99% |
57605
2.13 KIPS |
|
Text Classification (SP)
|
100% |
3180
4.24 KIPS |
|
Text Classification (HP)
|
100% |
2982
3.98 KIPS |
|
Text Classification (Q)
|
93% |
3005
4.03 KIPS |
|
Machine Translation (SP)
|
100% |
3101
53.4 IPS |
|
Machine Translation (HP)
|
100% |
6150
105.9 IPS |
|
Machine Translation (Q)
|
98% |
6860
118.5 IPS |