Upload Date | May 09 2024 08:40 AM |
Views | 2 |
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% |
459
86.0 IPS |
|
Image Classification (F16)
|
100% |
656
122.8 IPS |
|
Image Classification (I8)
|
99% |
657
123.0 IPS |
|
Image Segmentation (F32)
|
100% |
293
4.90 IPS |
|
Image Segmentation (F16)
|
100% |
350
5.84 IPS |
|
Image Segmentation (I8)
|
100% |
352
5.88 IPS |
|
Pose Estimation (F32)
|
100% |
2499
3.03 IPS |
|
Pose Estimation (F16)
|
100% |
2250
2.72 IPS |
|
Pose Estimation (I8)
|
100% |
2257
2.73 IPS |
|
Object Detection (F32)
|
100% |
499
37.2 IPS |
|
Object Detection (F16)
|
100% |
761
56.8 IPS |
|
Object Detection (I8)
|
97% |
498
37.2 IPS |
|
Face Detection (F32)
|
100% |
1084
12.9 IPS |
|
Face Detection (F16)
|
97% |
1832
21.8 IPS |
|
Face Detection (I8)
|
96% |
1829
21.8 IPS |
|
Depth Estimation (F32)
|
100% |
1323
10.3 IPS |
|
Depth Estimation (F16)
|
100% |
2370
18.4 IPS |
|
Depth Estimation (I8)
|
99% |
2395
18.6 IPS |
|
Style Transfer (F32)
|
100% |
4795
6.31 IPS |
|
Style Transfer (F16)
|
100% |
7499
9.86 IPS |
|
Style Transfer (I8)
|
100% |
7459
9.81 IPS |
|
Image Super-Resolution (F32)
|
100% |
1233
44.0 IPS |
|
Image Super-Resolution (F16)
|
100% |
1469
52.4 IPS |
|
Image Super-Resolution (I8)
|
100% |
1488
53.1 IPS |
|
Text Classification (F32)
|
100% |
270
388.5 IPS |
|
Text Classification (F16)
|
100% |
514
738.8 IPS |
|
Text Classification (I8)
|
96% |
513
737.7 IPS |
|
Machine Translation (F32)
|
100% |
448
8.24 IPS |
|
Machine Translation (F16)
|
100% |
598
11.0 IPS |
|
Machine Translation (I8)
|
99% |
447
8.23 IPS |