Upload Date | May 09 2024 08:29 AM |
Views | 2 |
System Information | |
---|---|
Operating System | iOS 17.4.1 |
Model | iPad Pro (10.5-inch) |
Model ID | iPad7,4 |
Motherboard | J208AP |
CPU Information | |
---|---|
Name | Apple A10X Fusion |
Topology | 1 Processor, 3 Cores |
Identifier | ARM |
Base Frequency | 2.34 GHz |
Cluster 1 | 3 Cores |
L1 Instruction Cache | 64.0 KB x 1 |
L1 Data Cache | 64.0 KB x 1 |
L2 Cache | 8.00 MB x 1 |
Memory Information | |
---|---|
Size | 3.91 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
323
60.5 IPS |
|
Image Classification (F16)
|
100% |
14
2.61 IPS |
|
Image Classification (I8)
|
99% |
14
2.61 IPS |
|
Image Segmentation (F32)
|
100% |
222
3.70 IPS |
|
Image Segmentation (F16)
|
100% |
18
0.30 IPS |
|
Image Segmentation (I8)
|
100% |
18
0.30 IPS |
|
Pose Estimation (F32)
|
100% |
1625
1.97 IPS |
|
Pose Estimation (F16)
|
100% |
20
0.02 IPS |
|
Pose Estimation (I8)
|
100% |
20
0.02 IPS |
|
Object Detection (F32)
|
100% |
337
25.2 IPS |
|
Object Detection (F16)
|
100% |
14
1.06 IPS |
|
Object Detection (I8)
|
97% |
345
25.7 IPS |
|
Face Detection (F32)
|
100% |
697
8.29 IPS |
|
Face Detection (F16)
|
98% |
45
0.53 IPS |
|
Face Detection (I8)
|
97% |
45
0.53 IPS |
|
Depth Estimation (F32)
|
100% |
824
6.39 IPS |
|
Depth Estimation (F16)
|
100% |
31
0.24 IPS |
|
Depth Estimation (I8)
|
99% |
31
0.24 IPS |
|
Style Transfer (F32)
|
100% |
2538
3.34 IPS |
|
Style Transfer (F16)
|
100% |
66
0.09 IPS |
|
Style Transfer (I8)
|
100% |
66
0.09 IPS |
|
Image Super-Resolution (F32)
|
100% |
771
27.5 IPS |
|
Image Super-Resolution (F16)
|
100% |
14
0.51 IPS |
|
Image Super-Resolution (I8)
|
100% |
14
0.51 IPS |
|
Text Classification (F32)
|
100% |
237
340.2 IPS |
|
Text Classification (F16)
|
100% |
200
287.0 IPS |
|
Text Classification (I8)
|
96% |
201
288.6 IPS |
|
Machine Translation (F32)
|
100% |
327
6.02 IPS |
|
Machine Translation (F16)
|
100% |
32
0.59 IPS |
|
Machine Translation (I8)
|
99% |
326
6.01 IPS |