Upload Date | May 08 2024 01:34 PM |
Views | 1 |
System Information | |
---|---|
Operating System | iOS 17.4.1 |
Model | iPad Pro (11-inch) |
Model ID | iPad8,1 |
Motherboard | J317AP |
CPU Information | |
---|---|
Name | Apple A12X Bionic |
Topology | 1 Processor, 8 Cores |
Identifier | ARM |
Base Frequency | 2.49 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
L1 Instruction Cache | 48.0 KB x 1 |
L1 Data Cache | 32.0 KB x 1 |
L2 Cache | 2.00 MB x 1 |
Memory Information | |
---|---|
Size | 3.69 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
471
88.1 IPS |
|
Image Classification (F16)
|
100% |
671
125.6 IPS |
|
Image Classification (I8)
|
99% |
665
124.5 IPS |
|
Image Segmentation (F32)
|
100% |
292
4.88 IPS |
|
Image Segmentation (F16)
|
100% |
356
5.94 IPS |
|
Image Segmentation (I8)
|
100% |
353
5.89 IPS |
|
Pose Estimation (F32)
|
100% |
2491
3.02 IPS |
|
Pose Estimation (F16)
|
100% |
2273
2.75 IPS |
|
Pose Estimation (I8)
|
100% |
2253
2.73 IPS |
|
Object Detection (F32)
|
100% |
502
37.5 IPS |
|
Object Detection (F16)
|
100% |
781
58.3 IPS |
|
Object Detection (I8)
|
97% |
501
37.4 IPS |
|
Face Detection (F32)
|
100% |
1088
12.9 IPS |
|
Face Detection (F16)
|
97% |
1850
22.0 IPS |
|
Face Detection (I8)
|
96% |
1856
22.1 IPS |
|
Depth Estimation (F32)
|
100% |
1323
10.3 IPS |
|
Depth Estimation (F16)
|
100% |
2378
18.4 IPS |
|
Depth Estimation (I8)
|
99% |
2368
18.4 IPS |
|
Style Transfer (F32)
|
100% |
4706
6.19 IPS |
|
Style Transfer (F16)
|
100% |
7503
9.87 IPS |
|
Style Transfer (I8)
|
100% |
7430
9.77 IPS |
|
Image Super-Resolution (F32)
|
100% |
1235
44.1 IPS |
|
Image Super-Resolution (F16)
|
100% |
1462
52.2 IPS |
|
Image Super-Resolution (I8)
|
100% |
1478
52.8 IPS |
|
Text Classification (F32)
|
100% |
270
387.7 IPS |
|
Text Classification (F16)
|
100% |
517
742.3 IPS |
|
Text Classification (I8)
|
96% |
517
742.8 IPS |
|
Machine Translation (F32)
|
100% |
444
8.18 IPS |
|
Machine Translation (F16)
|
100% |
597
11.0 IPS |
|
Machine Translation (I8)
|
99% |
438
8.06 IPS |