Upload Date | November 09 2024 08:13 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 | iPad13,8 |
Motherboard | J522AP |
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% |
1390
258.5 IPS |
|
Image Classification (HP)
|
100% |
6148
1.14 KIPS |
|
Image Classification (Q)
|
96% |
5782
1.08 KIPS |
|
Image Segmentation (SP)
|
100% |
1376
22.3 IPS |
|
Image Segmentation (HP)
|
100% |
9761
158.2 IPS |
|
Image Segmentation (Q)
|
99% |
10078
163.4 IPS |
|
Pose Estimation (SP)
|
100% |
6519
7.61 IPS |
|
Pose Estimation (HP)
|
100% |
68588
80.0 IPS |
|
Pose Estimation (Q)
|
95% |
66151
77.5 IPS |
|
Object Detection (SP)
|
100% |
1518
120.4 IPS |
|
Object Detection (HP)
|
99% |
7244
576.3 IPS |
|
Object Detection (Q)
|
91% |
6652
531.5 IPS |
|
Face Detection (SP)
|
100% |
3038
36.1 IPS |
|
Face Detection (HP)
|
100% |
16623
197.5 IPS |
|
Face Detection (Q)
|
100% |
15239
181.1 IPS |
|
Depth Estimation (SP)
|
100% |
5820
44.8 IPS |
|
Depth Estimation (HP)
|
99% |
47399
365.2 IPS |
|
Depth Estimation (Q)
|
85% |
47157
368.5 IPS |
|
Style Transfer (SP)
|
100% |
17159
22.1 IPS |
|
Style Transfer (HP)
|
100% |
119914
154.2 IPS |
|
Style Transfer (Q)
|
96% |
114868
148.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
3793
140.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
22981
848.6 IPS |
|
Image Super-Resolution (Q)
|
99% |
23642
873.0 IPS |
|
Text Classification (SP)
|
100% |
2289
3.06 KIPS |
|
Text Classification (HP)
|
100% |
3974
5.30 KIPS |
|
Text Classification (Q)
|
93% |
3957
5.31 KIPS |
|
Machine Translation (SP)
|
100% |
2468
42.5 IPS |
|
Machine Translation (HP)
|
100% |
3226
55.6 IPS |
|
Machine Translation (Q)
|
98% |
3369
58.2 IPS |