Upload Date | September 17 2024 11:55 AM |
Views | 3 |
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% |
1722
320.3 IPS |
|
Image Classification (HP)
|
100% |
10698
1.99 KIPS |
|
Image Classification (Q)
|
97% |
15344
2.86 KIPS |
|
Image Segmentation (SP)
|
100% |
1611
26.1 IPS |
|
Image Segmentation (HP)
|
100% |
12923
209.5 IPS |
|
Image Segmentation (Q)
|
99% |
15919
258.1 IPS |
|
Pose Estimation (SP)
|
100% |
8196
9.56 IPS |
|
Pose Estimation (HP)
|
100% |
106703
124.5 IPS |
|
Pose Estimation (Q)
|
95% |
205894
241.3 IPS |
|
Object Detection (SP)
|
100% |
1779
141.1 IPS |
|
Object Detection (HP)
|
100% |
13579
1.08 KIPS |
|
Object Detection (Q)
|
91% |
19167
1.53 KIPS |
|
Face Detection (SP)
|
100% |
3175
37.7 IPS |
|
Face Detection (HP)
|
100% |
34252
407.0 IPS |
|
Face Detection (Q)
|
100% |
49323
586.1 IPS |
|
Depth Estimation (SP)
|
100% |
7125
54.9 IPS |
|
Depth Estimation (HP)
|
99% |
78394
604.0 IPS |
|
Depth Estimation (Q)
|
85% |
128828
1.01 KIPS |
|
Style Transfer (SP)
|
100% |
21175
27.2 IPS |
|
Style Transfer (HP)
|
100% |
204666
263.1 IPS |
|
Style Transfer (Q)
|
96% |
244678
315.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
4974
183.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
34242
1.26 KIPS |
|
Image Super-Resolution (Q)
|
99% |
55374
2.04 KIPS |
|
Text Classification (SP)
|
100% |
3195
4.26 KIPS |
|
Text Classification (HP)
|
100% |
3141
4.19 KIPS |
|
Text Classification (Q)
|
93% |
3232
4.34 KIPS |
|
Machine Translation (SP)
|
100% |
3082
53.1 IPS |
|
Machine Translation (HP)
|
100% |
6540
112.7 IPS |
|
Machine Translation (Q)
|
98% |
7316
126.4 IPS |