Upload Date | November 20 2024 11:52 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 18.2 |
Model | iPad Pro (11-inch 3rd generation) |
Model ID | iPad13,6 |
Motherboard | J518AP |
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% |
1400
260.3 IPS |
|
Image Classification (HP)
|
100% |
6441
1.20 KIPS |
|
Image Classification (Q)
|
96% |
5578
1.04 KIPS |
|
Image Segmentation (SP)
|
100% |
1392
22.6 IPS |
|
Image Segmentation (HP)
|
100% |
9753
158.1 IPS |
|
Image Segmentation (Q)
|
99% |
10106
163.8 IPS |
|
Pose Estimation (SP)
|
100% |
6535
7.63 IPS |
|
Pose Estimation (HP)
|
100% |
67603
78.9 IPS |
|
Pose Estimation (Q)
|
95% |
65666
77.0 IPS |
|
Object Detection (SP)
|
100% |
1514
120.1 IPS |
|
Object Detection (HP)
|
99% |
7219
574.2 IPS |
|
Object Detection (Q)
|
91% |
6685
534.1 IPS |
|
Face Detection (SP)
|
100% |
3038
36.1 IPS |
|
Face Detection (HP)
|
100% |
16471
195.7 IPS |
|
Face Detection (Q)
|
100% |
15353
182.4 IPS |
|
Depth Estimation (SP)
|
100% |
5823
44.9 IPS |
|
Depth Estimation (HP)
|
99% |
47504
366.0 IPS |
|
Depth Estimation (Q)
|
85% |
47928
374.5 IPS |
|
Style Transfer (SP)
|
100% |
17248
22.2 IPS |
|
Style Transfer (HP)
|
100% |
120443
154.8 IPS |
|
Style Transfer (Q)
|
96% |
112451
145.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
3745
138.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
23125
853.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
23777
878.0 IPS |
|
Text Classification (SP)
|
100% |
2286
3.05 KIPS |
|
Text Classification (HP)
|
100% |
3962
5.29 KIPS |
|
Text Classification (Q)
|
93% |
3988
5.35 KIPS |
|
Machine Translation (SP)
|
100% |
2504
43.1 IPS |
|
Machine Translation (HP)
|
100% |
3250
56.0 IPS |
|
Machine Translation (Q)
|
98% |
3421
59.1 IPS |