Upload Date | August 29 2024 11:36 PM |
Views | 1 |
System Information | |
---|---|
Operating System | iOS 16.6 |
Model | iPad Pro (12.9-inch 3rd Generation) |
Model ID | iPad8,5 |
Motherboard | J320AP |
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 | 3.66 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
878
164.2 IPS |
|
Image Classification (F16)
|
100% |
1142
213.6 IPS |
|
Image Classification (I8)
|
99% |
1135
212.4 IPS |
|
Image Segmentation (F32)
|
100% |
366
6.10 IPS |
|
Image Segmentation (F16)
|
100% |
375
6.26 IPS |
|
Image Segmentation (I8)
|
100% |
371
6.19 IPS |
|
Pose Estimation (F32)
|
100% |
3021
3.66 IPS |
|
Pose Estimation (F16)
|
100% |
3908
4.73 IPS |
|
Pose Estimation (I8)
|
100% |
3876
4.69 IPS |
|
Object Detection (F32)
|
100% |
875
65.3 IPS |
|
Object Detection (F16)
|
100% |
1117
83.4 IPS |
|
Object Detection (I8)
|
97% |
891
66.5 IPS |
|
Face Detection (F32)
|
100% |
3421
40.7 IPS |
|
Face Detection (F16)
|
97% |
3915
46.6 IPS |
|
Face Detection (I8)
|
96% |
3749
44.6 IPS |
|
Depth Estimation (F32)
|
100% |
3195
24.8 IPS |
|
Depth Estimation (F16)
|
100% |
4174
32.4 IPS |
|
Depth Estimation (I8)
|
99% |
4277
33.2 IPS |
|
Style Transfer (F32)
|
24% |
8138
10.7 IPS |
|
Style Transfer (F16)
|
30% |
11260
14.8 IPS |
|
Style Transfer (I8)
|
30% |
11171
14.7 IPS |
|
Image Super-Resolution (F32)
|
100% |
1697
60.6 IPS |
|
Image Super-Resolution (F16)
|
100% |
1983
70.8 IPS |
|
Image Super-Resolution (I8)
|
100% |
2080
74.3 IPS |
|
Text Classification (F32)
|
100% |
230
330.3 IPS |
|
Text Classification (F16)
|
100% |
266
382.7 IPS |
|
Text Classification (I8)
|
96% |
258
370.1 IPS |
|
Machine Translation (F32)
|
100% |
502
9.24 IPS |
|
Machine Translation (F16)
|
100% |
462
8.49 IPS |
|
Machine Translation (I8)
|
99% |
501
9.22 IPS |