Upload Date | September 18 2024 09:30 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 |
System Information | |
---|---|
Operating System | iOS 18.0 |
Model | iPad Pro (11-inch, 4th generation) |
Model ID | iPad14,3 |
Motherboard | J617AP |
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 | 7.37 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1385
257.5 IPS |
|
Image Classification (HP)
|
100% |
14489
2.69 KIPS |
|
Image Classification (Q)
|
96% |
14631
2.73 KIPS |
|
Image Segmentation (SP)
|
100% |
1523
24.7 IPS |
|
Image Segmentation (HP)
|
100% |
9762
158.3 IPS |
|
Image Segmentation (Q)
|
99% |
10923
177.1 IPS |
|
Pose Estimation (SP)
|
100% |
6871
8.02 IPS |
|
Pose Estimation (HP)
|
100% |
101766
118.7 IPS |
|
Pose Estimation (Q)
|
95% |
104879
122.9 IPS |
|
Object Detection (SP)
|
100% |
1568
124.3 IPS |
|
Object Detection (HP)
|
99% |
15006
1.19 KIPS |
|
Object Detection (Q)
|
91% |
17109
1.37 KIPS |
|
Face Detection (SP)
|
100% |
3128
37.2 IPS |
|
Face Detection (HP)
|
100% |
31902
379.1 IPS |
|
Face Detection (Q)
|
100% |
39632
470.9 IPS |
|
Depth Estimation (SP)
|
100% |
5663
43.6 IPS |
|
Depth Estimation (HP)
|
99% |
84739
652.9 IPS |
|
Depth Estimation (Q)
|
85% |
109186
853.2 IPS |
|
Style Transfer (SP)
|
100% |
18830
24.2 IPS |
|
Style Transfer (HP)
|
100% |
202528
260.4 IPS |
|
Style Transfer (Q)
|
96% |
188316
243.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
4051
149.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
39228
1.45 KIPS |
|
Image Super-Resolution (Q)
|
99% |
46749
1.73 KIPS |
|
Text Classification (SP)
|
100% |
2227
2.97 KIPS |
|
Text Classification (HP)
|
100% |
3714
4.96 KIPS |
|
Text Classification (Q)
|
93% |
3664
4.92 KIPS |
|
Machine Translation (SP)
|
100% |
3545
61.1 IPS |
|
Machine Translation (HP)
|
100% |
2371
40.8 IPS |
|
Machine Translation (Q)
|
98% |
2369
40.9 IPS |