User | jmvioque |
Upload Date | July 02 2025 08:39 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 18.5 |
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% |
1414
262.9 IPS |
|
Image Classification (HP)
|
100% |
6174
1.15 KIPS |
|
Image Classification (Q)
|
96% |
5826
1.09 KIPS |
|
Image Segmentation (SP)
|
100% |
1369
22.2 IPS |
|
Image Segmentation (HP)
|
100% |
9702
157.3 IPS |
|
Image Segmentation (Q)
|
99% |
10050
162.9 IPS |
|
Pose Estimation (SP)
|
100% |
6494
7.58 IPS |
|
Pose Estimation (HP)
|
100% |
68730
80.2 IPS |
|
Pose Estimation (Q)
|
95% |
66925
78.4 IPS |
|
Object Detection (SP)
|
100% |
1513
120.0 IPS |
|
Object Detection (HP)
|
99% |
7262
577.7 IPS |
|
Object Detection (Q)
|
91% |
6699
535.3 IPS |
|
Face Detection (SP)
|
100% |
3045
36.2 IPS |
|
Face Detection (HP)
|
100% |
16416
195.1 IPS |
|
Face Detection (Q)
|
100% |
15340
182.3 IPS |
|
Depth Estimation (SP)
|
100% |
5675
43.7 IPS |
|
Depth Estimation (HP)
|
99% |
46950
361.7 IPS |
|
Depth Estimation (Q)
|
85% |
47692
372.7 IPS |
|
Style Transfer (SP)
|
100% |
16954
21.8 IPS |
|
Style Transfer (HP)
|
100% |
119943
154.2 IPS |
|
Style Transfer (Q)
|
96% |
114966
148.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
3680
135.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
23107
853.2 IPS |
|
Image Super-Resolution (Q)
|
99% |
23614
872.0 IPS |
|
Text Classification (SP)
|
100% |
2292
3.06 KIPS |
|
Text Classification (HP)
|
100% |
3991
5.33 KIPS |
|
Text Classification (Q)
|
93% |
3952
5.30 KIPS |
|
Machine Translation (SP)
|
100% |
2489
42.9 IPS |
|
Machine Translation (HP)
|
100% |
3556
61.2 IPS |
|
Machine Translation (Q)
|
98% |
3667
63.4 IPS |