User | Hulkstern |
Upload Date | September 02 2024 03:48 PM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 18.1 |
Model | iPad Pro (12.9-inch 5th generation) |
Model ID | iPad13,10 |
Motherboard | J523AP |
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 | 7.35 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1407
261.6 IPS |
|
Image Classification (HP)
|
100% |
6261
1.16 KIPS |
|
Image Classification (Q)
|
99% |
6443
1.20 KIPS |
|
Image Segmentation (SP)
|
100% |
1376
22.3 IPS |
|
Image Segmentation (HP)
|
100% |
6176
100.1 IPS |
|
Image Segmentation (Q)
|
100% |
6163
99.9 IPS |
|
Pose Estimation (SP)
|
100% |
6527
7.62 IPS |
|
Pose Estimation (HP)
|
100% |
67402
78.6 IPS |
|
Pose Estimation (Q)
|
94% |
64926
76.2 IPS |
|
Object Detection (SP)
|
100% |
1515
120.2 IPS |
|
Object Detection (HP)
|
99% |
6912
549.8 IPS |
|
Object Detection (Q)
|
91% |
6721
537.0 IPS |
|
Face Detection (SP)
|
100% |
3039
36.1 IPS |
|
Face Detection (HP)
|
100% |
12655
150.4 IPS |
|
Face Detection (Q)
|
100% |
13753
163.4 IPS |
|
Depth Estimation (SP)
|
100% |
5755
44.3 IPS |
|
Depth Estimation (HP)
|
99% |
43317
333.7 IPS |
|
Depth Estimation (Q)
|
97% |
45874
354.7 IPS |
|
Style Transfer (SP)
|
100% |
17113
22.0 IPS |
|
Style Transfer (HP)
|
100% |
116525
149.8 IPS |
|
Style Transfer (Q)
|
100% |
122549
157.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
3739
138.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
23132
854.1 IPS |
|
Image Super-Resolution (Q)
|
98% |
23126
856.8 IPS |
|
Text Classification (SP)
|
100% |
2323
3.10 KIPS |
|
Text Classification (HP)
|
100% |
3863
5.16 KIPS |
|
Text Classification (Q)
|
93% |
3857
5.18 KIPS |
|
Machine Translation (SP)
|
100% |
2483
42.8 IPS |
|
Machine Translation (HP)
|
100% |
2314
39.9 IPS |
|
Machine Translation (Q)
|
98% |
2315
40.0 IPS |