User | tanousjm |
Upload Date | April 14 2025 02:19 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 18.4 |
Model | iPhone 16 Pro Max |
Model ID | iPhone17,2 |
Motherboard | D94AP |
CPU Information | |
---|---|
Name | Apple A18 Pro |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 4.04 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.45 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2065
384.1 IPS |
|
Image Classification (HP)
|
100% |
15383
2.86 KIPS |
|
Image Classification (Q)
|
97% |
20593
3.84 KIPS |
|
Image Segmentation (SP)
|
100% |
1981
32.1 IPS |
|
Image Segmentation (HP)
|
100% |
18359
297.6 IPS |
|
Image Segmentation (Q)
|
99% |
24149
391.5 IPS |
|
Pose Estimation (SP)
|
100% |
8919
10.4 IPS |
|
Pose Estimation (HP)
|
100% |
152563
178.0 IPS |
|
Pose Estimation (Q)
|
95% |
290817
340.9 IPS |
|
Object Detection (SP)
|
100% |
2336
185.3 IPS |
|
Object Detection (HP)
|
100% |
16430
1.30 KIPS |
|
Object Detection (Q)
|
91% |
22366
1.79 KIPS |
|
Face Detection (SP)
|
100% |
3855
45.8 IPS |
|
Face Detection (HP)
|
100% |
41204
489.6 IPS |
|
Face Detection (Q)
|
100% |
58190
691.4 IPS |
|
Depth Estimation (SP)
|
100% |
8183
63.0 IPS |
|
Depth Estimation (HP)
|
99% |
95961
739.3 IPS |
|
Depth Estimation (Q)
|
85% |
162226
1.27 KIPS |
|
Style Transfer (SP)
|
100% |
19952
25.6 IPS |
|
Style Transfer (HP)
|
100% |
245512
315.6 IPS |
|
Style Transfer (Q)
|
96% |
302629
390.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
5441
200.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
50362
1.86 KIPS |
|
Image Super-Resolution (Q)
|
99% |
84564
3.12 KIPS |
|
Text Classification (SP)
|
100% |
3385
4.52 KIPS |
|
Text Classification (HP)
|
100% |
4706
6.28 KIPS |
|
Text Classification (Q)
|
93% |
3134
4.21 KIPS |
|
Machine Translation (SP)
|
100% |
4194
72.2 IPS |
|
Machine Translation (HP)
|
100% |
9960
171.6 IPS |
|
Machine Translation (Q)
|
98% |
10725
185.3 IPS |