User | Pressure_P |
Upload Date | January 03 2025 05:50 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 |
System Information | |
---|---|
Operating System | iOS 18.2 |
Model | iPad Pro 11-inch (M4) |
Model ID | iPad16,3 |
Motherboard | J717AP |
CPU Information | |
---|---|
Name | Apple M4 |
Topology | 1 Processor, 9 Cores |
Identifier | ARM |
Base Frequency | 4.41 GHz |
Cluster 1 | 3 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 7.29 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1980
368.2 IPS |
|
Image Classification (HP)
|
100% |
18440
3.43 KIPS |
|
Image Classification (Q)
|
97% |
26360
4.92 KIPS |
|
Image Segmentation (SP)
|
100% |
2143
34.7 IPS |
|
Image Segmentation (HP)
|
100% |
22238
360.5 IPS |
|
Image Segmentation (Q)
|
99% |
30685
497.4 IPS |
|
Pose Estimation (SP)
|
100% |
10053
11.7 IPS |
|
Pose Estimation (HP)
|
100% |
123873
144.5 IPS |
|
Pose Estimation (Q)
|
95% |
234152
274.4 IPS |
|
Object Detection (SP)
|
100% |
2257
179.0 IPS |
|
Object Detection (HP)
|
100% |
19002
1.51 KIPS |
|
Object Detection (Q)
|
91% |
27781
2.22 KIPS |
|
Face Detection (SP)
|
100% |
3905
46.4 IPS |
|
Face Detection (HP)
|
100% |
42984
510.7 IPS |
|
Face Detection (Q)
|
100% |
64468
766.0 IPS |
|
Depth Estimation (SP)
|
100% |
8327
64.2 IPS |
|
Depth Estimation (HP)
|
99% |
100485
774.2 IPS |
|
Depth Estimation (Q)
|
85% |
172549
1.35 KIPS |
|
Style Transfer (SP)
|
100% |
25131
32.3 IPS |
|
Style Transfer (HP)
|
100% |
235584
302.8 IPS |
|
Style Transfer (Q)
|
96% |
299247
386.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
5837
215.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
48923
1.81 KIPS |
|
Image Super-Resolution (Q)
|
99% |
86171
3.18 KIPS |
|
Text Classification (SP)
|
100% |
2960
3.95 KIPS |
|
Text Classification (HP)
|
100% |
6388
8.53 KIPS |
|
Text Classification (Q)
|
93% |
6492
8.71 KIPS |
|
Machine Translation (SP)
|
100% |
3907
67.3 IPS |
|
Machine Translation (HP)
|
100% |
16824
289.8 IPS |
|
Machine Translation (Q)
|
98% |
18263
315.6 IPS |