Upload Date | May 18 2024 08:40 AM |
Views | 3 |
System Information | |
---|---|
Operating System | iOS 17.5 |
Model | iPad Pro (10.5-inch) |
Model ID | iPad7,3 |
Motherboard | J207AP |
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 | Neural Engine |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
244
45.7 IPS |
|
Image Classification (F16)
|
100% |
217
40.6 IPS |
|
Image Classification (I8)
|
99% |
217
40.6 IPS |
|
Image Segmentation (F32)
|
100% |
151
2.52 IPS |
|
Image Segmentation (F16)
|
100% |
149
2.49 IPS |
|
Image Segmentation (I8)
|
100% |
149
2.49 IPS |
|
Pose Estimation (F32)
|
100% |
1484
1.80 IPS |
|
Pose Estimation (F16)
|
100% |
1474
1.79 IPS |
|
Pose Estimation (I8)
|
100% |
1476
1.79 IPS |
|
Object Detection (F32)
|
100% |
270
20.1 IPS |
|
Object Detection (F16)
|
100% |
235
17.5 IPS |
|
Object Detection (I8)
|
97% |
265
19.8 IPS |
|
Face Detection (F32)
|
100% |
515
6.13 IPS |
|
Face Detection (F16)
|
100% |
493
5.86 IPS |
|
Face Detection (I8)
|
99% |
490
5.82 IPS |
|
Depth Estimation (F32)
|
100% |
627
4.86 IPS |
|
Depth Estimation (F16)
|
100% |
577
4.47 IPS |
|
Depth Estimation (I8)
|
99% |
576
4.46 IPS |
|
Style Transfer (F32)
|
100% |
1983
2.61 IPS |
|
Style Transfer (F16)
|
100% |
1954
2.57 IPS |
|
Style Transfer (I8)
|
100% |
1911
2.51 IPS |
|
Image Super-Resolution (F32)
|
100% |
596
21.3 IPS |
|
Image Super-Resolution (F16)
|
100% |
588
21.0 IPS |
|
Image Super-Resolution (I8)
|
100% |
587
21.0 IPS |
|
Text Classification (F32)
|
100% |
144
206.5 IPS |
|
Text Classification (F16)
|
100% |
118
170.2 IPS |
|
Text Classification (I8)
|
96% |
120
172.3 IPS |
|
Machine Translation (F32)
|
100% |
237
4.36 IPS |
|
Machine Translation (F16)
|
100% |
204
3.75 IPS |
|
Machine Translation (I8)
|
99% |
241
4.43 IPS |