Upload Date | September 17 2024 03:56 AM |
Views | 1 |
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% |
1723
320.4 IPS |
|
Image Classification (HP)
|
100% |
11031
2.05 KIPS |
|
Image Classification (Q)
|
97% |
15441
2.88 KIPS |
|
Image Segmentation (SP)
|
100% |
1620
26.3 IPS |
|
Image Segmentation (HP)
|
100% |
12941
209.8 IPS |
|
Image Segmentation (Q)
|
99% |
16094
260.9 IPS |
|
Pose Estimation (SP)
|
100% |
8371
9.77 IPS |
|
Pose Estimation (HP)
|
100% |
106331
124.1 IPS |
|
Pose Estimation (Q)
|
95% |
204095
239.2 IPS |
|
Object Detection (SP)
|
100% |
1834
145.5 IPS |
|
Object Detection (HP)
|
100% |
13656
1.08 KIPS |
|
Object Detection (Q)
|
91% |
19254
1.54 KIPS |
|
Face Detection (SP)
|
100% |
3224
38.3 IPS |
|
Face Detection (HP)
|
100% |
33669
400.1 IPS |
|
Face Detection (Q)
|
100% |
49076
583.1 IPS |
|
Depth Estimation (SP)
|
100% |
7318
56.4 IPS |
|
Depth Estimation (HP)
|
99% |
79043
609.0 IPS |
|
Depth Estimation (Q)
|
85% |
133693
1.05 KIPS |
|
Style Transfer (SP)
|
100% |
21947
28.2 IPS |
|
Style Transfer (HP)
|
100% |
202624
260.5 IPS |
|
Style Transfer (Q)
|
96% |
246280
317.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
5179
191.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
34350
1.27 KIPS |
|
Image Super-Resolution (Q)
|
99% |
54902
2.03 KIPS |
|
Text Classification (SP)
|
100% |
3193
4.26 KIPS |
|
Text Classification (HP)
|
100% |
3082
4.11 KIPS |
|
Text Classification (Q)
|
93% |
3099
4.16 KIPS |
|
Machine Translation (SP)
|
100% |
3123
53.8 IPS |
|
Machine Translation (HP)
|
100% |
6271
108.0 IPS |
|
Machine Translation (Q)
|
98% |
7504
129.7 IPS |