Upload Date | July 26 2024 05:49 PM |
Views | 1 |
System Information | |
---|---|
Operating System | iOS 17.5.1 |
Model | iPad Pro 11-inch (2nd generation) |
Model ID | iPad8,9 |
Motherboard | J417AP |
CPU Information | |
---|---|
Name | Apple A12Z 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 | 5.56 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
901
168.6 IPS |
|
Image Classification (F16)
|
100% |
2180
407.9 IPS |
|
Image Classification (I8)
|
99% |
2154
403.0 IPS |
|
Image Segmentation (F32)
|
100% |
252
4.20 IPS |
|
Image Segmentation (F16)
|
100% |
277
4.63 IPS |
|
Image Segmentation (I8)
|
100% |
257
4.29 IPS |
|
Pose Estimation (F32)
|
100% |
3019
3.66 IPS |
|
Pose Estimation (F16)
|
100% |
24634
29.8 IPS |
|
Pose Estimation (I8)
|
100% |
24587
29.8 IPS |
|
Object Detection (F32)
|
100% |
909
67.9 IPS |
|
Object Detection (F16)
|
100% |
1198
89.4 IPS |
|
Object Detection (I8)
|
97% |
914
68.2 IPS |
|
Face Detection (F32)
|
100% |
3423
40.7 IPS |
|
Face Detection (F16)
|
98% |
4189
49.8 IPS |
|
Face Detection (I8)
|
97% |
4334
51.5 IPS |
|
Depth Estimation (F32)
|
100% |
3290
25.5 IPS |
|
Depth Estimation (F16)
|
100% |
20458
158.7 IPS |
|
Depth Estimation (I8)
|
99% |
21462
166.4 IPS |
|
Style Transfer (F32)
|
100% |
8719
11.5 IPS |
|
Style Transfer (F16)
|
100% |
10482
13.8 IPS |
|
Style Transfer (I8)
|
100% |
10437
13.7 IPS |
|
Image Super-Resolution (F32)
|
100% |
1607
57.4 IPS |
|
Image Super-Resolution (F16)
|
100% |
3746
133.8 IPS |
|
Image Super-Resolution (I8)
|
100% |
3706
132.3 IPS |
|
Text Classification (F32)
|
100% |
208
298.9 IPS |
|
Text Classification (F16)
|
100% |
245
352.0 IPS |
|
Text Classification (I8)
|
96% |
245
352.8 IPS |
|
Machine Translation (F32)
|
100% |
362
6.66 IPS |
|
Machine Translation (F16)
|
100% |
356
6.55 IPS |
|
Machine Translation (I8)
|
99% |
361
6.65 IPS |