User | oldnick |
Upload Date | December 31 2024 12:57 PM |
Views | 3 |
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 | iPad16,4 |
Motherboard | J718AP |
CPU Information | |
---|---|
Name | Apple M4 |
Topology | 1 Processor, 10 Cores |
Identifier | ARM |
Base Frequency | 4.41 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 15.14 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2027
377.0 IPS |
|
Image Classification (HP)
|
100% |
17127
3.19 KIPS |
|
Image Classification (Q)
|
97% |
24829
4.63 KIPS |
|
Image Segmentation (SP)
|
100% |
2144
34.8 IPS |
|
Image Segmentation (HP)
|
100% |
21949
355.8 IPS |
|
Image Segmentation (Q)
|
99% |
30279
490.9 IPS |
|
Pose Estimation (SP)
|
100% |
10084
11.8 IPS |
|
Pose Estimation (HP)
|
100% |
123691
144.3 IPS |
|
Pose Estimation (Q)
|
95% |
233131
273.2 IPS |
|
Object Detection (SP)
|
100% |
2254
178.8 IPS |
|
Object Detection (HP)
|
100% |
19022
1.51 KIPS |
|
Object Detection (Q)
|
91% |
26468
2.11 KIPS |
|
Face Detection (SP)
|
100% |
3994
47.5 IPS |
|
Face Detection (HP)
|
100% |
42046
499.6 IPS |
|
Face Detection (Q)
|
100% |
62788
746.1 IPS |
|
Depth Estimation (SP)
|
100% |
8298
63.9 IPS |
|
Depth Estimation (HP)
|
99% |
99071
763.3 IPS |
|
Depth Estimation (Q)
|
85% |
169379
1.32 KIPS |
|
Style Transfer (SP)
|
100% |
25232
32.4 IPS |
|
Style Transfer (HP)
|
100% |
230583
296.4 IPS |
|
Style Transfer (Q)
|
96% |
298129
384.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
5877
217.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
48765
1.80 KIPS |
|
Image Super-Resolution (Q)
|
99% |
83844
3.10 KIPS |
|
Text Classification (SP)
|
100% |
2942
3.93 KIPS |
|
Text Classification (HP)
|
100% |
6102
8.15 KIPS |
|
Text Classification (Q)
|
93% |
6246
8.38 KIPS |
|
Machine Translation (SP)
|
100% |
3911
67.4 IPS |
|
Machine Translation (HP)
|
100% |
16442
283.2 IPS |
|
Machine Translation (Q)
|
98% |
18030
311.6 IPS |