Upload Date | November 09 2024 07:12 PM |
Views | 8 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 |
System Information | |
---|---|
Operating System | iOS 18.2 |
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 | 7.35 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
871
162.1 IPS |
|
Image Classification (HP)
|
100% |
10484
1.95 KIPS |
|
Image Classification (Q)
|
96% |
11727
2.19 KIPS |
|
Image Segmentation (SP)
|
100% |
1009
16.3 IPS |
|
Image Segmentation (HP)
|
100% |
13554
219.7 IPS |
|
Image Segmentation (Q)
|
99% |
16284
264.0 IPS |
|
Pose Estimation (SP)
|
100% |
4176
4.87 IPS |
|
Pose Estimation (HP)
|
100% |
67639
78.9 IPS |
|
Pose Estimation (Q)
|
95% |
66254
77.7 IPS |
|
Object Detection (SP)
|
100% |
1020
80.9 IPS |
|
Object Detection (HP)
|
99% |
11374
904.8 IPS |
|
Object Detection (Q)
|
91% |
11535
921.7 IPS |
|
Face Detection (SP)
|
100% |
2196
26.1 IPS |
|
Face Detection (HP)
|
100% |
21216
252.1 IPS |
|
Face Detection (Q)
|
100% |
26757
317.9 IPS |
|
Depth Estimation (SP)
|
100% |
3606
27.8 IPS |
|
Depth Estimation (HP)
|
99% |
60169
463.6 IPS |
|
Depth Estimation (Q)
|
85% |
73434
573.9 IPS |
|
Style Transfer (SP)
|
100% |
11758
15.1 IPS |
|
Style Transfer (HP)
|
100% |
137357
176.6 IPS |
|
Style Transfer (Q)
|
96% |
128913
166.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
2612
96.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
28167
1.04 KIPS |
|
Image Super-Resolution (Q)
|
99% |
33769
1.25 KIPS |
|
Text Classification (SP)
|
100% |
1522
2.03 KIPS |
|
Text Classification (HP)
|
100% |
2370
3.16 KIPS |
|
Text Classification (Q)
|
93% |
2389
3.21 KIPS |
|
Machine Translation (SP)
|
100% |
2504
43.1 IPS |
|
Machine Translation (HP)
|
100% |
2898
49.9 IPS |
|
Machine Translation (Q)
|
98% |
2982
51.5 IPS |