Upload Date | December 07 2024 09:04 AM |
Views | 2 |
System Information | |
---|---|
Operating System | iOS 16.7.10 |
Model | iPad Pro (9.7-inch) |
Model ID | iPad6,4 |
Motherboard | J128AP |
CPU Information | |
---|---|
Name | Apple A9X |
Topology | 1 Processor, 2 Cores |
Identifier | ARM |
Base Frequency | 2.26 GHz |
Cluster 1 | 2 Cores |
L1 Instruction Cache | 64.0 KB x 1 |
L1 Data Cache | 64.0 KB x 1 |
L2 Cache | 3.00 MB x 1 |
Memory Information | |
---|---|
Size | 1.92 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
225
42.1 IPS |
|
Image Classification (F16)
|
100% |
216
40.4 IPS |
|
Image Classification (I8)
|
99% |
204
38.2 IPS |
|
Image Segmentation (F32)
|
100% |
170
2.84 IPS |
|
Image Segmentation (F16)
|
100% |
172
2.88 IPS |
|
Image Segmentation (I8)
|
100% |
175
2.92 IPS |
|
Pose Estimation (F32)
|
100% |
2053
2.49 IPS |
|
Pose Estimation (F16)
|
100% |
2016
2.44 IPS |
|
Pose Estimation (I8)
|
100% |
2025
2.45 IPS |
|
Object Detection (F32)
|
100% |
298
22.2 IPS |
|
Object Detection (F16)
|
100% |
271
20.3 IPS |
|
Object Detection (I8)
|
97% |
299
22.3 IPS |
|
Face Detection (F32)
|
100% |
1229
14.6 IPS |
|
Face Detection (F16)
|
100% |
1166
13.9 IPS |
|
Face Detection (I8)
|
99% |
1158
13.8 IPS |
|
Depth Estimation (F32)
|
100% |
2286
17.7 IPS |
|
Depth Estimation (F16)
|
100% |
2117
16.4 IPS |
|
Depth Estimation (I8)
|
99% |
2168
16.8 IPS |
|
Style Transfer (F32)
|
100% |
5391
7.09 IPS |
|
Style Transfer (F16)
|
100% |
4808
6.32 IPS |
|
Style Transfer (I8)
|
100% |
4710
6.20 IPS |
|
Image Super-Resolution (F32)
|
100% |
1156
41.3 IPS |
|
Image Super-Resolution (F16)
|
100% |
1115
39.8 IPS |
|
Image Super-Resolution (I8)
|
100% |
1156
41.3 IPS |
|
Text Classification (F32)
|
100% |
53
76.0 IPS |
|
Text Classification (F16)
|
100% |
97
139.8 IPS |
|
Text Classification (I8)
|
96% |
97
139.4 IPS |
|
Machine Translation (F32)
|
100% |
131
2.41 IPS |
|
Machine Translation (F16)
|
100% |
112
2.05 IPS |
|
Machine Translation (I8)
|
99% |
132
2.42 IPS |