Upload Date | May 08 2024 10:06 PM |
Views | 3 |
System Information | |
---|---|
Operating System | iOS 17.4.1 |
Model | iPad Pro 12.9-inch (4th generation) |
Model ID | iPad8,11 |
Motherboard | J420AP |
CPU Information | |
---|---|
Name | Apple A12Z 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 | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
1119
209.5 IPS |
|
Image Classification (F16)
|
100% |
1277
239.0 IPS |
|
Image Classification (I8)
|
99% |
1305
244.1 IPS |
|
Image Segmentation (F32)
|
100% |
253
4.22 IPS |
|
Image Segmentation (F16)
|
100% |
270
4.51 IPS |
|
Image Segmentation (I8)
|
100% |
270
4.52 IPS |
|
Pose Estimation (F32)
|
100% |
2892
3.50 IPS |
|
Pose Estimation (F16)
|
100% |
4187
5.07 IPS |
|
Pose Estimation (I8)
|
100% |
4070
4.93 IPS |
|
Object Detection (F32)
|
100% |
694
51.8 IPS |
|
Object Detection (F16)
|
100% |
861
64.3 IPS |
|
Object Detection (I8)
|
97% |
817
61.0 IPS |
|
Face Detection (F32)
|
100% |
2718
32.3 IPS |
|
Face Detection (F16)
|
98% |
4354
51.8 IPS |
|
Face Detection (I8)
|
97% |
3066
36.5 IPS |
|
Depth Estimation (F32)
|
100% |
2582
20.0 IPS |
|
Depth Estimation (F16)
|
100% |
4000
31.0 IPS |
|
Depth Estimation (I8)
|
99% |
3977
30.8 IPS |
|
Style Transfer (F32)
|
100% |
8133
10.7 IPS |
|
Style Transfer (F16)
|
100% |
8287
10.9 IPS |
|
Style Transfer (I8)
|
100% |
10618
14.0 IPS |
|
Image Super-Resolution (F32)
|
100% |
1753
62.6 IPS |
|
Image Super-Resolution (F16)
|
100% |
2373
84.7 IPS |
|
Image Super-Resolution (I8)
|
100% |
2433
86.9 IPS |
|
Text Classification (F32)
|
100% |
212
304.0 IPS |
|
Text Classification (F16)
|
100% |
251
361.0 IPS |
|
Text Classification (I8)
|
96% |
252
362.7 IPS |
|
Machine Translation (F32)
|
100% |
355
6.53 IPS |
|
Machine Translation (F16)
|
100% |
345
6.35 IPS |
|
Machine Translation (I8)
|
99% |
356
6.54 IPS |