Upload Date | November 20 2024 06:56 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 18.1.1 |
Model | iPad Pro (11-inch 3rd generation) |
Model ID | iPad13,4 |
Motherboard | J517AP |
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 | 7.37 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1394
259.3 IPS |
|
Image Classification (HP)
|
100% |
5986
1.11 KIPS |
|
Image Classification (Q)
|
96% |
5705
1.07 KIPS |
|
Image Segmentation (SP)
|
100% |
1415
22.9 IPS |
|
Image Segmentation (HP)
|
100% |
9819
159.2 IPS |
|
Image Segmentation (Q)
|
99% |
10060
163.1 IPS |
|
Pose Estimation (SP)
|
100% |
6531
7.62 IPS |
|
Pose Estimation (HP)
|
100% |
66920
78.1 IPS |
|
Pose Estimation (Q)
|
95% |
65760
77.1 IPS |
|
Object Detection (SP)
|
100% |
1515
120.1 IPS |
|
Object Detection (HP)
|
99% |
7344
584.2 IPS |
|
Object Detection (Q)
|
91% |
6701
535.4 IPS |
|
Face Detection (SP)
|
100% |
3032
36.0 IPS |
|
Face Detection (HP)
|
100% |
16624
197.5 IPS |
|
Face Detection (Q)
|
100% |
15393
182.9 IPS |
|
Depth Estimation (SP)
|
100% |
5794
44.6 IPS |
|
Depth Estimation (HP)
|
99% |
47344
364.8 IPS |
|
Depth Estimation (Q)
|
85% |
47334
369.9 IPS |
|
Style Transfer (SP)
|
100% |
17180
22.1 IPS |
|
Style Transfer (HP)
|
100% |
119857
154.1 IPS |
|
Style Transfer (Q)
|
96% |
111988
144.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
3749
138.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
23175
855.8 IPS |
|
Image Super-Resolution (Q)
|
99% |
23712
875.6 IPS |
|
Text Classification (SP)
|
100% |
2300
3.07 KIPS |
|
Text Classification (HP)
|
100% |
3808
5.08 KIPS |
|
Text Classification (Q)
|
93% |
3805
5.11 KIPS |
|
Machine Translation (SP)
|
100% |
2478
42.7 IPS |
|
Machine Translation (HP)
|
100% |
5378
92.6 IPS |
|
Machine Translation (Q)
|
98% |
5617
97.1 IPS |