Upload Date | December 22 2024 04:02 AM |
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 | iPad13,7 |
Motherboard | J518xAP |
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 | 15.37 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1392
258.8 IPS |
|
Image Classification (HP)
|
100% |
6300
1.17 KIPS |
|
Image Classification (Q)
|
96% |
5888
1.10 KIPS |
|
Image Segmentation (SP)
|
100% |
1386
22.5 IPS |
|
Image Segmentation (HP)
|
100% |
9745
158.0 IPS |
|
Image Segmentation (Q)
|
99% |
10005
162.2 IPS |
|
Pose Estimation (SP)
|
100% |
6534
7.62 IPS |
|
Pose Estimation (HP)
|
100% |
66842
78.0 IPS |
|
Pose Estimation (Q)
|
95% |
65668
77.0 IPS |
|
Object Detection (SP)
|
100% |
1522
120.7 IPS |
|
Object Detection (HP)
|
99% |
7230
575.2 IPS |
|
Object Detection (Q)
|
91% |
6690
534.5 IPS |
|
Face Detection (SP)
|
100% |
3048
36.2 IPS |
|
Face Detection (HP)
|
100% |
16504
196.1 IPS |
|
Face Detection (Q)
|
100% |
15326
182.1 IPS |
|
Depth Estimation (SP)
|
100% |
5776
44.5 IPS |
|
Depth Estimation (HP)
|
99% |
47266
364.2 IPS |
|
Depth Estimation (Q)
|
85% |
48070
375.6 IPS |
|
Style Transfer (SP)
|
100% |
17164
22.1 IPS |
|
Style Transfer (HP)
|
100% |
119973
154.2 IPS |
|
Style Transfer (Q)
|
96% |
112357
145.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
3751
138.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
22990
848.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
23814
879.3 IPS |
|
Text Classification (SP)
|
100% |
2287
3.05 KIPS |
|
Text Classification (HP)
|
100% |
3837
5.12 KIPS |
|
Text Classification (Q)
|
93% |
3845
5.16 KIPS |
|
Machine Translation (SP)
|
100% |
2476
42.6 IPS |
|
Machine Translation (HP)
|
100% |
3220
55.5 IPS |
|
Machine Translation (Q)
|
98% |
3419
59.1 IPS |