User | iGeneration |
Upload Date | December 30 2024 11:01 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M4 |
System Information | |
---|---|
Operating System | iOS 18.1.1 |
Model | iPad Pro 11-inch (M4) |
Model ID | iPad16,4 |
Motherboard | J718AP |
CPU Information | |
---|---|
Name | Apple M4 |
Topology | 1 Processor, 9 Cores |
Identifier | ARM |
Base Frequency | 4.41 GHz |
Cluster 1 | 3 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 7.29 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
4487
834.4 IPS |
|
Image Classification (HP)
|
100% |
4824
897.1 IPS |
|
Image Classification (Q)
|
97% |
4125
769.8 IPS |
|
Image Segmentation (SP)
|
100% |
4970
80.6 IPS |
|
Image Segmentation (HP)
|
100% |
6783
110.0 IPS |
|
Image Segmentation (Q)
|
99% |
7185
116.5 IPS |
|
Pose Estimation (SP)
|
100% |
28230
32.9 IPS |
|
Pose Estimation (HP)
|
100% |
30099
35.1 IPS |
|
Pose Estimation (Q)
|
95% |
28606
33.5 IPS |
|
Object Detection (SP)
|
100% |
4806
381.2 IPS |
|
Object Detection (HP)
|
100% |
5218
413.9 IPS |
|
Object Detection (Q)
|
91% |
4431
354.1 IPS |
|
Face Detection (SP)
|
100% |
12976
154.2 IPS |
|
Face Detection (HP)
|
100% |
16440
195.3 IPS |
|
Face Detection (Q)
|
100% |
11991
142.5 IPS |
|
Depth Estimation (SP)
|
100% |
20365
156.9 IPS |
|
Depth Estimation (HP)
|
99% |
22412
172.7 IPS |
|
Depth Estimation (Q)
|
85% |
19042
148.8 IPS |
|
Style Transfer (SP)
|
100% |
58587
75.3 IPS |
|
Style Transfer (HP)
|
100% |
67953
87.4 IPS |
|
Style Transfer (Q)
|
96% |
63862
82.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
11633
429.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
12697
468.8 IPS |
|
Image Super-Resolution (Q)
|
99% |
10266
379.1 IPS |
|
Text Classification (SP)
|
100% |
3000
4.00 KIPS |
|
Text Classification (HP)
|
100% |
5260
7.02 KIPS |
|
Text Classification (Q)
|
93% |
5175
6.95 KIPS |
|
Machine Translation (SP)
|
100% |
1965
33.9 IPS |
|
Machine Translation (HP)
|
100% |
1644
28.3 IPS |
|
Machine Translation (Q)
|
98% |
1648
28.5 IPS |