Upload Date | September 18 2024 01:50 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.1 |
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% |
1622
301.7 IPS |
|
Image Classification (HP)
|
100% |
10884
2.02 KIPS |
|
Image Classification (Q)
|
97% |
15257
2.85 KIPS |
|
Image Segmentation (SP)
|
100% |
1669
27.1 IPS |
|
Image Segmentation (HP)
|
100% |
12760
206.8 IPS |
|
Image Segmentation (Q)
|
99% |
15753
255.4 IPS |
|
Pose Estimation (SP)
|
100% |
7358
8.59 IPS |
|
Pose Estimation (HP)
|
100% |
105016
122.5 IPS |
|
Pose Estimation (Q)
|
95% |
202362
237.2 IPS |
|
Object Detection (SP)
|
100% |
1754
139.2 IPS |
|
Object Detection (HP)
|
100% |
13684
1.09 KIPS |
|
Object Detection (Q)
|
91% |
19291
1.54 KIPS |
|
Face Detection (SP)
|
100% |
3131
37.2 IPS |
|
Face Detection (HP)
|
100% |
33403
396.9 IPS |
|
Face Detection (Q)
|
100% |
49195
584.5 IPS |
|
Depth Estimation (SP)
|
100% |
7020
54.1 IPS |
|
Depth Estimation (HP)
|
99% |
78532
605.0 IPS |
|
Depth Estimation (Q)
|
85% |
128233
1.00 KIPS |
|
Style Transfer (SP)
|
100% |
20402
26.2 IPS |
|
Style Transfer (HP)
|
100% |
205168
263.7 IPS |
|
Style Transfer (Q)
|
96% |
251886
325.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
4857
179.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
34187
1.26 KIPS |
|
Image Super-Resolution (Q)
|
99% |
57322
2.12 KIPS |
|
Text Classification (SP)
|
100% |
3186
4.25 KIPS |
|
Text Classification (HP)
|
100% |
2126
2.84 KIPS |
|
Text Classification (Q)
|
93% |
2075
2.79 KIPS |
|
Machine Translation (SP)
|
100% |
3120
53.7 IPS |
|
Machine Translation (HP)
|
100% |
6154
106.0 IPS |
|
Machine Translation (Q)
|
98% |
7766
134.2 IPS |