User | Aaronage |
Upload Date | December 10 2024 11:42 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M4 |
System Information | |
---|---|
Operating System | iOS 18.1.1 |
Model | iPad Pro 13-inch (M4) |
Model ID | iPad16,5 |
Motherboard | J720AP |
CPU Information | |
---|---|
Name | Apple M4 |
Topology | 1 Processor, 10 Cores |
Identifier | ARM |
Base Frequency | 4.41 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 15.07 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
4503
837.4 IPS |
|
Image Classification (HP)
|
100% |
4819
896.1 IPS |
|
Image Classification (Q)
|
97% |
4219
787.3 IPS |
|
Image Segmentation (SP)
|
100% |
4887
79.2 IPS |
|
Image Segmentation (HP)
|
100% |
6771
109.8 IPS |
|
Image Segmentation (Q)
|
99% |
7184
116.4 IPS |
|
Pose Estimation (SP)
|
100% |
28220
32.9 IPS |
|
Pose Estimation (HP)
|
100% |
30134
35.2 IPS |
|
Pose Estimation (Q)
|
95% |
28667
33.6 IPS |
|
Object Detection (SP)
|
100% |
4788
379.8 IPS |
|
Object Detection (HP)
|
100% |
5211
413.4 IPS |
|
Object Detection (Q)
|
91% |
4443
355.1 IPS |
|
Face Detection (SP)
|
100% |
12728
151.2 IPS |
|
Face Detection (HP)
|
100% |
16501
196.1 IPS |
|
Face Detection (Q)
|
100% |
11972
142.2 IPS |
|
Depth Estimation (SP)
|
100% |
20522
158.1 IPS |
|
Depth Estimation (HP)
|
99% |
22382
172.4 IPS |
|
Depth Estimation (Q)
|
85% |
19031
148.8 IPS |
|
Style Transfer (SP)
|
100% |
58356
75.0 IPS |
|
Style Transfer (HP)
|
100% |
67868
87.2 IPS |
|
Style Transfer (Q)
|
96% |
63840
82.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
11728
433.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
12731
470.1 IPS |
|
Image Super-Resolution (Q)
|
99% |
10435
385.3 IPS |
|
Text Classification (SP)
|
100% |
2964
3.96 KIPS |
|
Text Classification (HP)
|
100% |
5672
7.57 KIPS |
|
Text Classification (Q)
|
93% |
5444
7.31 KIPS |
|
Machine Translation (SP)
|
100% |
1975
34.0 IPS |
|
Machine Translation (HP)
|
100% |
1614
27.8 IPS |
|
Machine Translation (Q)
|
98% |
1649
28.5 IPS |