Upload Date | November 09 2024 03:54 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 |
System Information | |
---|---|
Operating System | iOS 18.1 |
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% |
1225
227.7 IPS |
|
Image Classification (HP)
|
100% |
13043
2.43 KIPS |
|
Image Classification (Q)
|
96% |
15524
2.90 KIPS |
|
Image Segmentation (SP)
|
100% |
1488
24.1 IPS |
|
Image Segmentation (HP)
|
100% |
18528
300.3 IPS |
|
Image Segmentation (Q)
|
99% |
24060
390.0 IPS |
|
Pose Estimation (SP)
|
100% |
6856
8.00 IPS |
|
Pose Estimation (HP)
|
100% |
104885
122.4 IPS |
|
Pose Estimation (Q)
|
95% |
104881
122.9 IPS |
|
Object Detection (SP)
|
100% |
1560
123.8 IPS |
|
Object Detection (HP)
|
99% |
15660
1.25 KIPS |
|
Object Detection (Q)
|
91% |
16944
1.35 KIPS |
|
Face Detection (SP)
|
100% |
3129
37.2 IPS |
|
Face Detection (HP)
|
100% |
33622
399.5 IPS |
|
Face Detection (Q)
|
100% |
42169
501.1 IPS |
|
Depth Estimation (SP)
|
100% |
5711
44.0 IPS |
|
Depth Estimation (HP)
|
99% |
85898
661.8 IPS |
|
Depth Estimation (Q)
|
85% |
105321
823.0 IPS |
|
Style Transfer (SP)
|
100% |
18888
24.3 IPS |
|
Style Transfer (HP)
|
100% |
201782
259.4 IPS |
|
Style Transfer (Q)
|
96% |
193819
250.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
4156
153.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
38282
1.41 KIPS |
|
Image Super-Resolution (Q)
|
99% |
46107
1.70 KIPS |
|
Text Classification (SP)
|
100% |
2198
2.93 KIPS |
|
Text Classification (HP)
|
100% |
3700
4.94 KIPS |
|
Text Classification (Q)
|
93% |
3690
4.95 KIPS |
|
Machine Translation (SP)
|
100% |
3519
60.6 IPS |
|
Machine Translation (HP)
|
100% |
6707
115.5 IPS |
|
Machine Translation (Q)
|
98% |
7385
127.6 IPS |