Upload Date | November 09 2024 06:17 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 |
System Information | |
---|---|
Operating System | iOS 18.1 |
Model | iPad Pro (12.9-inch, 6th generation) |
Model ID | iPad14,5 |
Motherboard | J620AP |
CPU Information | |
---|---|
Name | Apple M2 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM |
Base Frequency | 3.49 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 15.35 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1386
257.8 IPS |
|
Image Classification (HP)
|
100% |
14009
2.61 KIPS |
|
Image Classification (Q)
|
96% |
15195
2.84 KIPS |
|
Image Segmentation (SP)
|
100% |
1533
24.9 IPS |
|
Image Segmentation (HP)
|
100% |
18599
301.5 IPS |
|
Image Segmentation (Q)
|
99% |
23228
376.5 IPS |
|
Pose Estimation (SP)
|
100% |
6884
8.03 IPS |
|
Pose Estimation (HP)
|
100% |
101617
118.6 IPS |
|
Pose Estimation (Q)
|
95% |
104600
122.6 IPS |
|
Object Detection (SP)
|
100% |
1566
124.2 IPS |
|
Object Detection (HP)
|
99% |
14949
1.19 KIPS |
|
Object Detection (Q)
|
91% |
16578
1.32 KIPS |
|
Face Detection (SP)
|
100% |
3156
37.5 IPS |
|
Face Detection (HP)
|
100% |
32859
390.4 IPS |
|
Face Detection (Q)
|
100% |
41995
499.0 IPS |
|
Depth Estimation (SP)
|
100% |
5678
43.7 IPS |
|
Depth Estimation (HP)
|
99% |
84898
654.1 IPS |
|
Depth Estimation (Q)
|
85% |
104965
820.3 IPS |
|
Style Transfer (SP)
|
100% |
18826
24.2 IPS |
|
Style Transfer (HP)
|
100% |
200167
257.3 IPS |
|
Style Transfer (Q)
|
96% |
187326
241.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
4045
149.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
38274
1.41 KIPS |
|
Image Super-Resolution (Q)
|
99% |
45107
1.67 KIPS |
|
Text Classification (SP)
|
100% |
2261
3.02 KIPS |
|
Text Classification (HP)
|
100% |
3814
5.09 KIPS |
|
Text Classification (Q)
|
93% |
3762
5.05 KIPS |
|
Machine Translation (SP)
|
100% |
3549
61.1 IPS |
|
Machine Translation (HP)
|
100% |
6666
114.8 IPS |
|
Machine Translation (Q)
|
98% |
7240
125.1 IPS |