Upload Date | November 13 2024 03:39 PM |
Views | 1 |
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 | Neural Engine |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
247
46.2 IPS |
|
Image Classification (F16)
|
100% |
232
43.4 IPS |
|
Image Classification (I8)
|
99% |
248
46.5 IPS |
|
Image Segmentation (F32)
|
100% |
180
3.01 IPS |
|
Image Segmentation (F16)
|
100% |
181
3.02 IPS |
|
Image Segmentation (I8)
|
100% |
180
3.00 IPS |
|
Pose Estimation (F32)
|
100% |
2044
2.48 IPS |
|
Pose Estimation (F16)
|
100% |
2035
2.46 IPS |
|
Pose Estimation (I8)
|
100% |
2017
2.44 IPS |
|
Object Detection (F32)
|
100% |
348
26.0 IPS |
|
Object Detection (F16)
|
100% |
292
21.8 IPS |
|
Object Detection (I8)
|
97% |
324
24.2 IPS |
|
Face Detection (F32)
|
100% |
1263
15.0 IPS |
|
Face Detection (F16)
|
100% |
1178
14.0 IPS |
|
Face Detection (I8)
|
99% |
1034
12.3 IPS |
|
Depth Estimation (F32)
|
100% |
2002
15.5 IPS |
|
Depth Estimation (F16)
|
100% |
2008
15.6 IPS |
|
Depth Estimation (I8)
|
99% |
1969
15.3 IPS |
|
Style Transfer (F32)
|
100% |
4128
5.43 IPS |
|
Style Transfer (F16)
|
100% |
4085
5.37 IPS |
|
Style Transfer (I8)
|
100% |
4091
5.38 IPS |
|
Image Super-Resolution (F32)
|
100% |
875
31.3 IPS |
|
Image Super-Resolution (F16)
|
100% |
839
29.9 IPS |
|
Image Super-Resolution (I8)
|
100% |
831
29.7 IPS |
|
Text Classification (F32)
|
100% |
65
93.4 IPS |
|
Text Classification (F16)
|
100% |
92
131.8 IPS |
|
Text Classification (I8)
|
96% |
95
136.0 IPS |
|
Machine Translation (F32)
|
100% |
130
2.39 IPS |
|
Machine Translation (F16)
|
100% |
117
2.15 IPS |
|
Machine Translation (I8)
|
99% |
138
2.53 IPS |