Upload Date | August 29 2024 12:39 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 | Neural Engine |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
855
160.1 IPS |
|
Image Classification (F16)
|
100% |
2279
426.4 IPS |
|
Image Classification (I8)
|
99% |
2271
425.0 IPS |
|
Image Segmentation (F32)
|
100% |
349
5.83 IPS |
|
Image Segmentation (F16)
|
100% |
395
6.60 IPS |
|
Image Segmentation (I8)
|
100% |
395
6.60 IPS |
|
Pose Estimation (F32)
|
100% |
3038
3.68 IPS |
|
Pose Estimation (F16)
|
100% |
25686
31.1 IPS |
|
Pose Estimation (I8)
|
100% |
25730
31.2 IPS |
|
Object Detection (F32)
|
100% |
866
64.7 IPS |
|
Object Detection (F16)
|
100% |
1141
85.2 IPS |
|
Object Detection (I8)
|
97% |
921
68.7 IPS |
|
Face Detection (F32)
|
100% |
3372
40.1 IPS |
|
Face Detection (F16)
|
97% |
3827
45.5 IPS |
|
Face Detection (I8)
|
96% |
3725
44.3 IPS |
|
Depth Estimation (F32)
|
100% |
3124
24.2 IPS |
|
Depth Estimation (F16)
|
100% |
19760
153.2 IPS |
|
Depth Estimation (I8)
|
99% |
19632
152.2 IPS |
|
Style Transfer (F32)
|
24% |
8309
10.9 IPS |
|
Style Transfer (F16)
|
30% |
11199
14.7 IPS |
|
Style Transfer (I8)
|
30% |
11181
14.7 IPS |
|
Image Super-Resolution (F32)
|
100% |
1596
57.0 IPS |
|
Image Super-Resolution (F16)
|
100% |
3815
136.2 IPS |
|
Image Super-Resolution (I8)
|
100% |
3709
132.5 IPS |
|
Text Classification (F32)
|
100% |
217
312.4 IPS |
|
Text Classification (F16)
|
100% |
264
379.9 IPS |
|
Text Classification (I8)
|
96% |
260
373.9 IPS |
|
Machine Translation (F32)
|
100% |
493
9.06 IPS |
|
Machine Translation (F16)
|
100% |
460
8.47 IPS |
|
Machine Translation (I8)
|
99% |
494
9.09 IPS |