Upload Date | September 17 2024 12:50 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.0 |
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% |
1711
318.2 IPS |
|
Image Classification (HP)
|
100% |
10900
2.03 KIPS |
|
Image Classification (Q)
|
97% |
14831
2.77 KIPS |
|
Image Segmentation (SP)
|
100% |
1622
26.3 IPS |
|
Image Segmentation (HP)
|
100% |
12902
209.1 IPS |
|
Image Segmentation (Q)
|
99% |
16049
260.2 IPS |
|
Pose Estimation (SP)
|
100% |
8236
9.61 IPS |
|
Pose Estimation (HP)
|
100% |
106649
124.4 IPS |
|
Pose Estimation (Q)
|
95% |
204154
239.3 IPS |
|
Object Detection (SP)
|
100% |
1803
143.0 IPS |
|
Object Detection (HP)
|
100% |
13708
1.09 KIPS |
|
Object Detection (Q)
|
91% |
19230
1.54 KIPS |
|
Face Detection (SP)
|
100% |
3194
37.9 IPS |
|
Face Detection (HP)
|
100% |
34490
409.8 IPS |
|
Face Detection (Q)
|
100% |
49198
584.6 IPS |
|
Depth Estimation (SP)
|
100% |
7183
55.3 IPS |
|
Depth Estimation (HP)
|
99% |
79123
609.6 IPS |
|
Depth Estimation (Q)
|
85% |
128792
1.01 KIPS |
|
Style Transfer (SP)
|
100% |
21174
27.2 IPS |
|
Style Transfer (HP)
|
100% |
206668
265.7 IPS |
|
Style Transfer (Q)
|
96% |
251684
324.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
4925
181.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
34187
1.26 KIPS |
|
Image Super-Resolution (Q)
|
99% |
56909
2.10 KIPS |
|
Text Classification (SP)
|
100% |
3219
4.30 KIPS |
|
Text Classification (HP)
|
100% |
3494
4.66 KIPS |
|
Text Classification (Q)
|
93% |
3147
4.22 KIPS |
|
Machine Translation (SP)
|
100% |
3121
53.8 IPS |
|
Machine Translation (HP)
|
100% |
6208
106.9 IPS |
|
Machine Translation (Q)
|
98% |
7976
137.8 IPS |