Upload Date | May 11 2024 03:09 PM |
Views | 7 |
System Information | |
---|---|
Operating System | iOS 17.5 |
Model | iPad14,6 |
Model ID | iPad14,6 |
Motherboard | J621AP |
CPU Information | |
---|---|
Name | ARM |
Topology | 1 Processor, 8 Cores |
Identifier | ARM |
Base Frequency | 3.49 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
L1 Instruction Cache | 128 KB x 1 |
L1 Data Cache | 64.0 KB x 1 |
L2 Cache | 4.00 MB x 1 |
Memory Information | |
---|---|
Size | 15.31 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
3302
617.8 IPS |
|
Image Classification (F16)
|
100% |
3442
644.0 IPS |
|
Image Classification (I8)
|
99% |
2992
559.8 IPS |
|
Image Segmentation (F32)
|
100% |
1430
23.9 IPS |
|
Image Segmentation (F16)
|
100% |
1517
25.3 IPS |
|
Image Segmentation (I8)
|
100% |
1516
25.3 IPS |
|
Pose Estimation (F32)
|
100% |
22641
27.4 IPS |
|
Pose Estimation (F16)
|
100% |
24988
30.3 IPS |
|
Pose Estimation (I8)
|
100% |
24570
29.8 IPS |
|
Object Detection (F32)
|
100% |
2818
210.4 IPS |
|
Object Detection (F16)
|
100% |
2831
211.4 IPS |
|
Object Detection (I8)
|
97% |
2586
193.0 IPS |
|
Face Detection (F32)
|
100% |
9287
110.4 IPS |
|
Face Detection (F16)
|
98% |
10562
125.6 IPS |
|
Face Detection (I8)
|
97% |
10151
120.7 IPS |
|
Depth Estimation (F32)
|
100% |
15992
124.0 IPS |
|
Depth Estimation (F16)
|
100% |
17390
134.9 IPS |
|
Depth Estimation (I8)
|
37% |
16170
125.4 IPS |
|
Style Transfer (F32)
|
100% |
39420
51.9 IPS |
|
Style Transfer (F16)
|
100% |
47023
61.9 IPS |
|
Style Transfer (I8)
|
100% |
42742
56.2 IPS |
|
Image Super-Resolution (F32)
|
100% |
7757
277.0 IPS |
|
Image Super-Resolution (F16)
|
100% |
10091
360.4 IPS |
|
Image Super-Resolution (I8)
|
100% |
9860
352.1 IPS |
|
Text Classification (F32)
|
100% |
1112
1.60 KIPS |
|
Text Classification (F16)
|
100% |
732
1.05 KIPS |
|
Text Classification (I8)
|
96% |
731
1.05 KIPS |
|
Machine Translation (F32)
|
100% |
790
14.5 IPS |
|
Machine Translation (F16)
|
100% |
801
14.7 IPS |
|
Machine Translation (I8)
|
99% |
759
14.0 IPS |