Upload Date | November 19 2024 12:56 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% |
1400
260.3 IPS |
|
Image Classification (HP)
|
100% |
6278
1.17 KIPS |
|
Image Classification (Q)
|
96% |
5834
1.09 KIPS |
|
Image Segmentation (SP)
|
100% |
1382
22.4 IPS |
|
Image Segmentation (HP)
|
100% |
9718
157.5 IPS |
|
Image Segmentation (Q)
|
99% |
9962
161.5 IPS |
|
Pose Estimation (SP)
|
100% |
6522
7.61 IPS |
|
Pose Estimation (HP)
|
100% |
68617
80.1 IPS |
|
Pose Estimation (Q)
|
95% |
66382
77.8 IPS |
|
Object Detection (SP)
|
100% |
1519
120.5 IPS |
|
Object Detection (HP)
|
99% |
7213
573.8 IPS |
|
Object Detection (Q)
|
91% |
6695
534.9 IPS |
|
Face Detection (SP)
|
100% |
3053
36.3 IPS |
|
Face Detection (HP)
|
100% |
16547
196.6 IPS |
|
Face Detection (Q)
|
100% |
15317
182.0 IPS |
|
Depth Estimation (SP)
|
100% |
5834
44.9 IPS |
|
Depth Estimation (HP)
|
99% |
47298
364.4 IPS |
|
Depth Estimation (Q)
|
85% |
47462
370.9 IPS |
|
Style Transfer (SP)
|
100% |
17143
22.0 IPS |
|
Style Transfer (HP)
|
100% |
119778
154.0 IPS |
|
Style Transfer (Q)
|
96% |
114907
148.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
3765
139.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
23061
851.5 IPS |
|
Image Super-Resolution (Q)
|
99% |
23678
874.3 IPS |
|
Text Classification (SP)
|
100% |
2286
3.05 KIPS |
|
Text Classification (HP)
|
100% |
3969
5.30 KIPS |
|
Text Classification (Q)
|
93% |
3937
5.28 KIPS |
|
Machine Translation (SP)
|
100% |
2497
43.0 IPS |
|
Machine Translation (HP)
|
100% |
3226
55.6 IPS |
|
Machine Translation (Q)
|
98% |
3424
59.2 IPS |