Upload Date | November 21 2024 08:29 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.2 |
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% |
1439
267.7 IPS |
|
Image Classification (HP)
|
100% |
10331
1.92 KIPS |
|
Image Classification (Q)
|
97% |
12806
2.39 KIPS |
|
Image Segmentation (SP)
|
100% |
1427
23.1 IPS |
|
Image Segmentation (HP)
|
100% |
13978
226.6 IPS |
|
Image Segmentation (Q)
|
99% |
18056
292.7 IPS |
|
Pose Estimation (SP)
|
100% |
7129
8.32 IPS |
|
Pose Estimation (HP)
|
100% |
99669
116.3 IPS |
|
Pose Estimation (Q)
|
95% |
101441
118.9 IPS |
|
Object Detection (SP)
|
100% |
1573
124.8 IPS |
|
Object Detection (HP)
|
100% |
12829
1.02 KIPS |
|
Object Detection (Q)
|
91% |
14636
1.17 KIPS |
|
Face Detection (SP)
|
100% |
3037
36.1 IPS |
|
Face Detection (HP)
|
100% |
29449
349.9 IPS |
|
Face Detection (Q)
|
100% |
38549
458.0 IPS |
|
Depth Estimation (SP)
|
100% |
6149
47.4 IPS |
|
Depth Estimation (HP)
|
99% |
75786
583.9 IPS |
|
Depth Estimation (Q)
|
85% |
95232
744.6 IPS |
|
Style Transfer (SP)
|
100% |
18880
24.3 IPS |
|
Style Transfer (HP)
|
100% |
166003
213.4 IPS |
|
Style Transfer (Q)
|
96% |
167337
215.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
4237
156.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
31614
1.17 KIPS |
|
Image Super-Resolution (Q)
|
99% |
36961
1.36 KIPS |
|
Text Classification (SP)
|
100% |
2613
3.49 KIPS |
|
Text Classification (HP)
|
100% |
2340
3.12 KIPS |
|
Text Classification (Q)
|
93% |
2401
3.22 KIPS |
|
Machine Translation (SP)
|
100% |
3426
59.0 IPS |
|
Machine Translation (HP)
|
100% |
7113
122.5 IPS |
|
Machine Translation (Q)
|
98% |
7641
132.0 IPS |