User | karen_he |
Upload Date | August 15 2024 07:31 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 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% |
1531
284.8 IPS |
|
Image Classification (HP)
|
100% |
11091
2.06 KIPS |
|
Image Classification (Q)
|
99% |
13340
2.49 KIPS |
|
Image Segmentation (SP)
|
100% |
1559
25.3 IPS |
|
Image Segmentation (HP)
|
100% |
11043
179.0 IPS |
|
Image Segmentation (Q)
|
100% |
11401
184.8 IPS |
|
Pose Estimation (SP)
|
100% |
7296
8.51 IPS |
|
Pose Estimation (HP)
|
100% |
99103
115.6 IPS |
|
Pose Estimation (Q)
|
94% |
199149
233.6 IPS |
|
Object Detection (SP)
|
100% |
1724
136.7 IPS |
|
Object Detection (HP)
|
100% |
13099
1.04 KIPS |
|
Object Detection (Q)
|
91% |
19136
1.53 KIPS |
|
Face Detection (SP)
|
100% |
2641
31.4 IPS |
|
Face Detection (HP)
|
100% |
21782
258.8 IPS |
|
Face Detection (Q)
|
100% |
35337
419.9 IPS |
|
Depth Estimation (SP)
|
100% |
6638
51.1 IPS |
|
Depth Estimation (HP)
|
99% |
63911
492.4 IPS |
|
Depth Estimation (Q)
|
97% |
74641
577.1 IPS |
|
Style Transfer (SP)
|
100% |
19105
24.6 IPS |
|
Style Transfer (HP)
|
100% |
137736
177.1 IPS |
|
Style Transfer (Q)
|
100% |
137234
176.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
4518
166.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
36417
1.34 KIPS |
|
Image Super-Resolution (Q)
|
98% |
49681
1.84 KIPS |
|
Text Classification (SP)
|
100% |
3211
4.29 KIPS |
|
Text Classification (HP)
|
100% |
1997
2.67 KIPS |
|
Text Classification (Q)
|
93% |
1947
2.61 KIPS |
|
Machine Translation (SP)
|
100% |
2903
50.0 IPS |
|
Machine Translation (HP)
|
100% |
6108
105.2 IPS |
|
Machine Translation (Q)
|
98% |
6127
105.9 IPS |