Upload Date | May 09 2024 08:40 AM |
Views | 1 |
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 | Neural Engine |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
243
45.4 IPS |
|
Image Classification (F16)
|
100% |
212
39.7 IPS |
|
Image Classification (I8)
|
99% |
216
40.5 IPS |
|
Image Segmentation (F32)
|
100% |
152
2.54 IPS |
|
Image Segmentation (F16)
|
100% |
152
2.55 IPS |
|
Image Segmentation (I8)
|
100% |
153
2.55 IPS |
|
Pose Estimation (F32)
|
100% |
1493
1.81 IPS |
|
Pose Estimation (F16)
|
100% |
1481
1.79 IPS |
|
Pose Estimation (I8)
|
100% |
1485
1.80 IPS |
|
Object Detection (F32)
|
100% |
278
20.7 IPS |
|
Object Detection (F16)
|
100% |
245
18.3 IPS |
|
Object Detection (I8)
|
97% |
279
20.8 IPS |
|
Face Detection (F32)
|
100% |
532
6.33 IPS |
|
Face Detection (F16)
|
100% |
524
6.23 IPS |
|
Face Detection (I8)
|
99% |
524
6.23 IPS |
|
Depth Estimation (F32)
|
100% |
692
5.36 IPS |
|
Depth Estimation (F16)
|
100% |
626
4.86 IPS |
|
Depth Estimation (I8)
|
99% |
625
4.85 IPS |
|
Style Transfer (F32)
|
100% |
2184
2.87 IPS |
|
Style Transfer (F16)
|
100% |
2178
2.87 IPS |
|
Style Transfer (I8)
|
100% |
2181
2.87 IPS |
|
Image Super-Resolution (F32)
|
100% |
680
24.3 IPS |
|
Image Super-Resolution (F16)
|
100% |
667
23.8 IPS |
|
Image Super-Resolution (I8)
|
100% |
672
24.0 IPS |
|
Text Classification (F32)
|
100% |
162
232.2 IPS |
|
Text Classification (F16)
|
100% |
141
202.0 IPS |
|
Text Classification (I8)
|
96% |
133
191.5 IPS |
|
Machine Translation (F32)
|
100% |
250
4.60 IPS |
|
Machine Translation (F16)
|
100% |
212
3.90 IPS |
|
Machine Translation (I8)
|
99% |
251
4.61 IPS |