User | Risto3 |
Upload Date | November 06 2024 02:53 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 18.2 |
Model | iPad Pro (12.9-inch 5th generation) |
Model ID | iPad13,11 |
Motherboard | J523xAP |
CPU Information | |
---|---|
Name | Apple M1 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM |
Base Frequency | 3.19 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 15.35 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1395
259.5 IPS |
|
Image Classification (HP)
|
100% |
6153
1.14 KIPS |
|
Image Classification (Q)
|
96% |
5927
1.11 KIPS |
|
Image Segmentation (SP)
|
100% |
1418
23.0 IPS |
|
Image Segmentation (HP)
|
100% |
9768
158.3 IPS |
|
Image Segmentation (Q)
|
99% |
9978
161.7 IPS |
|
Pose Estimation (SP)
|
100% |
6511
7.60 IPS |
|
Pose Estimation (HP)
|
100% |
69303
80.9 IPS |
|
Pose Estimation (Q)
|
95% |
65662
77.0 IPS |
|
Object Detection (SP)
|
100% |
1509
119.7 IPS |
|
Object Detection (HP)
|
99% |
7352
584.9 IPS |
|
Object Detection (Q)
|
91% |
6644
530.9 IPS |
|
Face Detection (SP)
|
100% |
3050
36.2 IPS |
|
Face Detection (HP)
|
100% |
16496
196.0 IPS |
|
Face Detection (Q)
|
100% |
15240
181.1 IPS |
|
Depth Estimation (SP)
|
100% |
5728
44.1 IPS |
|
Depth Estimation (HP)
|
99% |
48267
371.9 IPS |
|
Depth Estimation (Q)
|
85% |
48254
377.1 IPS |
|
Style Transfer (SP)
|
100% |
17251
22.2 IPS |
|
Style Transfer (HP)
|
100% |
120113
154.4 IPS |
|
Style Transfer (Q)
|
96% |
114018
147.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
3812
140.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
23385
863.5 IPS |
|
Image Super-Resolution (Q)
|
99% |
23386
863.5 IPS |
|
Text Classification (SP)
|
100% |
2323
3.10 KIPS |
|
Text Classification (HP)
|
100% |
4054
5.41 KIPS |
|
Text Classification (Q)
|
93% |
4045
5.43 KIPS |
|
Machine Translation (SP)
|
100% |
2564
44.2 IPS |
|
Machine Translation (HP)
|
100% |
3238
55.8 IPS |
|
Machine Translation (Q)
|
98% |
3331
57.6 IPS |