User | Rohan_C |
Upload Date | October 12 2024 12:46 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.0.1 |
Model | iPhone 14 Pro Max |
Model ID | iPhone15,3 |
Motherboard | D74AP |
CPU Information | |
---|---|
Name | Apple A16 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.46 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 5.51 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1435
266.9 IPS |
|
Image Classification (HP)
|
100% |
10291
1.91 KIPS |
|
Image Classification (Q)
|
97% |
12920
2.41 KIPS |
|
Image Segmentation (SP)
|
100% |
1422
23.1 IPS |
|
Image Segmentation (HP)
|
100% |
11789
191.1 IPS |
|
Image Segmentation (Q)
|
99% |
13842
224.4 IPS |
|
Pose Estimation (SP)
|
100% |
6984
8.15 IPS |
|
Pose Estimation (HP)
|
100% |
96048
112.1 IPS |
|
Pose Estimation (Q)
|
95% |
101492
119.0 IPS |
|
Object Detection (SP)
|
100% |
1572
124.7 IPS |
|
Object Detection (HP)
|
100% |
12922
1.02 KIPS |
|
Object Detection (Q)
|
91% |
15001
1.20 KIPS |
|
Face Detection (SP)
|
100% |
2919
34.7 IPS |
|
Face Detection (HP)
|
100% |
29954
355.9 IPS |
|
Face Detection (Q)
|
100% |
38545
458.0 IPS |
|
Depth Estimation (SP)
|
100% |
6279
48.4 IPS |
|
Depth Estimation (HP)
|
99% |
74881
576.9 IPS |
|
Depth Estimation (Q)
|
85% |
96549
754.9 IPS |
|
Style Transfer (SP)
|
100% |
18702
24.0 IPS |
|
Style Transfer (HP)
|
100% |
175006
225.0 IPS |
|
Style Transfer (Q)
|
96% |
167422
216.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
4171
154.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
33944
1.25 KIPS |
|
Image Super-Resolution (Q)
|
99% |
37072
1.37 KIPS |
|
Text Classification (SP)
|
100% |
2678
3.57 KIPS |
|
Text Classification (HP)
|
100% |
2033
2.71 KIPS |
|
Text Classification (Q)
|
93% |
2603
3.49 KIPS |
|
Machine Translation (SP)
|
100% |
3396
58.5 IPS |
|
Machine Translation (HP)
|
100% |
2436
42.0 IPS |
|
Machine Translation (Q)
|
98% |
2418
41.8 IPS |