Upload Date | July 10 2024 08:43 PM |
Views | 1 |
System Information | |
---|---|
Operating System | iOS 17.5.1 |
Model | iPad Pro (11-inch) |
Model ID | iPad8,1 |
Motherboard | J317AP |
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 | 3.69 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
464
86.8 IPS |
|
Image Classification (F16)
|
100% |
655
122.6 IPS |
|
Image Classification (I8)
|
99% |
664
124.2 IPS |
|
Image Segmentation (F32)
|
100% |
295
4.93 IPS |
|
Image Segmentation (F16)
|
100% |
352
5.88 IPS |
|
Image Segmentation (I8)
|
100% |
351
5.85 IPS |
|
Pose Estimation (F32)
|
100% |
2494
3.02 IPS |
|
Pose Estimation (F16)
|
100% |
2265
2.74 IPS |
|
Pose Estimation (I8)
|
100% |
2262
2.74 IPS |
|
Object Detection (F32)
|
100% |
499
37.2 IPS |
|
Object Detection (F16)
|
100% |
780
58.2 IPS |
|
Object Detection (I8)
|
97% |
499
37.3 IPS |
|
Face Detection (F32)
|
100% |
1083
12.9 IPS |
|
Face Detection (F16)
|
97% |
1836
21.8 IPS |
|
Face Detection (I8)
|
96% |
1838
21.9 IPS |
|
Depth Estimation (F32)
|
100% |
1327
10.3 IPS |
|
Depth Estimation (F16)
|
100% |
2360
18.3 IPS |
|
Depth Estimation (I8)
|
99% |
2399
18.6 IPS |
|
Style Transfer (F32)
|
100% |
4794
6.31 IPS |
|
Style Transfer (F16)
|
100% |
7497
9.86 IPS |
|
Style Transfer (I8)
|
100% |
7475
9.83 IPS |
|
Image Super-Resolution (F32)
|
100% |
1221
43.6 IPS |
|
Image Super-Resolution (F16)
|
100% |
1447
51.7 IPS |
|
Image Super-Resolution (I8)
|
100% |
1440
51.4 IPS |
|
Text Classification (F32)
|
100% |
269
386.0 IPS |
|
Text Classification (F16)
|
100% |
519
746.6 IPS |
|
Text Classification (I8)
|
96% |
521
749.1 IPS |
|
Machine Translation (F32)
|
100% |
450
8.28 IPS |
|
Machine Translation (F16)
|
100% |
600
11.0 IPS |
|
Machine Translation (I8)
|
99% |
450
8.27 IPS |