Upload Date | June 11 2024 07:00 PM |
Views | 1 |
System Information | |
---|---|
Operating System | iOS 17.5.1 |
Model | iPad Pro 12.9-inch (4th generation) |
Model ID | iPad8,12 |
Motherboard | J421AP |
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% |
913
170.8 IPS |
|
Image Classification (F16)
|
100% |
1085
203.1 IPS |
|
Image Classification (I8)
|
99% |
1052
196.9 IPS |
|
Image Segmentation (F32)
|
100% |
249
4.15 IPS |
|
Image Segmentation (F16)
|
100% |
263
4.39 IPS |
|
Image Segmentation (I8)
|
100% |
262
4.38 IPS |
|
Pose Estimation (F32)
|
100% |
3018
3.65 IPS |
|
Pose Estimation (F16)
|
100% |
4411
5.34 IPS |
|
Pose Estimation (I8)
|
100% |
4454
5.39 IPS |
|
Object Detection (F32)
|
100% |
874
65.2 IPS |
|
Object Detection (F16)
|
100% |
1154
86.1 IPS |
|
Object Detection (I8)
|
97% |
892
66.6 IPS |
|
Face Detection (F32)
|
100% |
3436
40.9 IPS |
|
Face Detection (F16)
|
98% |
3915
46.5 IPS |
|
Face Detection (I8)
|
97% |
3924
46.7 IPS |
|
Depth Estimation (F32)
|
100% |
3223
25.0 IPS |
|
Depth Estimation (F16)
|
100% |
4855
37.7 IPS |
|
Depth Estimation (I8)
|
99% |
4883
37.9 IPS |
|
Style Transfer (F32)
|
100% |
8720
11.5 IPS |
|
Style Transfer (F16)
|
100% |
10516
13.8 IPS |
|
Style Transfer (I8)
|
100% |
10360
13.6 IPS |
|
Image Super-Resolution (F32)
|
100% |
1703
60.8 IPS |
|
Image Super-Resolution (F16)
|
100% |
2337
83.5 IPS |
|
Image Super-Resolution (I8)
|
100% |
2450
87.5 IPS |
|
Text Classification (F32)
|
100% |
215
308.9 IPS |
|
Text Classification (F16)
|
100% |
257
369.9 IPS |
|
Text Classification (I8)
|
96% |
258
370.3 IPS |
|
Machine Translation (F32)
|
100% |
362
6.66 IPS |
|
Machine Translation (F16)
|
100% |
356
6.55 IPS |
|
Machine Translation (I8)
|
99% |
363
6.67 IPS |