User | bittenapple |
Upload Date | August 16 2024 08:49 AM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.1 |
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% |
1490
277.1 IPS |
|
Image Classification (HP)
|
100% |
11197
2.08 KIPS |
|
Image Classification (Q)
|
99% |
12895
2.41 KIPS |
|
Image Segmentation (SP)
|
100% |
1515
24.6 IPS |
|
Image Segmentation (HP)
|
100% |
10794
175.0 IPS |
|
Image Segmentation (Q)
|
100% |
10836
175.7 IPS |
|
Pose Estimation (SP)
|
100% |
6940
8.10 IPS |
|
Pose Estimation (HP)
|
100% |
98004
114.4 IPS |
|
Pose Estimation (Q)
|
94% |
197249
231.4 IPS |
|
Object Detection (SP)
|
100% |
1632
129.4 IPS |
|
Object Detection (HP)
|
100% |
13079
1.04 KIPS |
|
Object Detection (Q)
|
91% |
18712
1.50 KIPS |
|
Face Detection (SP)
|
100% |
3000
35.6 IPS |
|
Face Detection (HP)
|
100% |
21839
259.5 IPS |
|
Face Detection (Q)
|
100% |
34670
412.0 IPS |
|
Depth Estimation (SP)
|
100% |
6518
50.2 IPS |
|
Depth Estimation (HP)
|
99% |
63957
492.8 IPS |
|
Depth Estimation (Q)
|
97% |
73560
568.8 IPS |
|
Style Transfer (SP)
|
100% |
18661
24.0 IPS |
|
Style Transfer (HP)
|
100% |
137640
176.9 IPS |
|
Style Transfer (Q)
|
100% |
138326
177.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
4386
162.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
33751
1.25 KIPS |
|
Image Super-Resolution (Q)
|
98% |
53802
1.99 KIPS |
|
Text Classification (SP)
|
100% |
3154
4.21 KIPS |
|
Text Classification (HP)
|
100% |
2033
2.71 KIPS |
|
Text Classification (Q)
|
93% |
2151
2.89 KIPS |
|
Machine Translation (SP)
|
100% |
3065
52.8 IPS |
|
Machine Translation (HP)
|
100% |
6004
103.4 IPS |
|
Machine Translation (Q)
|
98% |
7245
125.2 IPS |