Upload Date | May 08 2024 02:34 PM |
Views | 2 |
System Information | |
---|---|
Operating System | iOS 17.4.1 |
Model | iPad Pro (12.9-inch 3rd Generation) |
Model ID | iPad8,6 |
Motherboard | J320xAP |
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 | 5.53 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
462
86.4 IPS |
|
Image Classification (F16)
|
100% |
683
127.8 IPS |
|
Image Classification (I8)
|
99% |
683
127.9 IPS |
|
Image Segmentation (F32)
|
100% |
295
4.92 IPS |
|
Image Segmentation (F16)
|
100% |
353
5.89 IPS |
|
Image Segmentation (I8)
|
100% |
352
5.88 IPS |
|
Pose Estimation (F32)
|
100% |
2505
3.03 IPS |
|
Pose Estimation (F16)
|
100% |
2260
2.74 IPS |
|
Pose Estimation (I8)
|
100% |
2306
2.79 IPS |
|
Object Detection (F32)
|
100% |
491
36.7 IPS |
|
Object Detection (F16)
|
100% |
766
57.2 IPS |
|
Object Detection (I8)
|
97% |
491
36.7 IPS |
|
Face Detection (F32)
|
100% |
1082
12.9 IPS |
|
Face Detection (F16)
|
97% |
1832
21.8 IPS |
|
Face Detection (I8)
|
96% |
1836
21.8 IPS |
|
Depth Estimation (F32)
|
100% |
1338
10.4 IPS |
|
Depth Estimation (F16)
|
100% |
2410
18.7 IPS |
|
Depth Estimation (I8)
|
99% |
2409
18.7 IPS |
|
Style Transfer (F32)
|
100% |
4809
6.33 IPS |
|
Style Transfer (F16)
|
100% |
7560
9.94 IPS |
|
Style Transfer (I8)
|
100% |
7571
9.96 IPS |
|
Image Super-Resolution (F32)
|
100% |
1233
44.0 IPS |
|
Image Super-Resolution (F16)
|
100% |
1550
55.3 IPS |
|
Image Super-Resolution (I8)
|
100% |
1522
54.4 IPS |
|
Text Classification (F32)
|
100% |
268
385.3 IPS |
|
Text Classification (F16)
|
100% |
514
738.7 IPS |
|
Text Classification (I8)
|
96% |
515
740.2 IPS |
|
Machine Translation (F32)
|
100% |
446
8.20 IPS |
|
Machine Translation (F16)
|
100% |
598
11.0 IPS |
|
Machine Translation (I8)
|
99% |
445
8.20 IPS |