Upload Date | January 23 2024 11:29 PM |
Views | 1 |
System Information | |
---|---|
Operating System | iOS 17.3 |
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% |
861
161.0 IPS |
|
Image Classification (F16)
|
100% |
2150
402.3 IPS |
|
Image Classification (I8)
|
99% |
2149
402.1 IPS |
|
Image Segmentation (F32)
|
100% |
249
4.16 IPS |
|
Image Segmentation (F16)
|
100% |
258
4.31 IPS |
|
Image Segmentation (I8)
|
100% |
264
4.41 IPS |
|
Pose Estimation (F32)
|
100% |
3035
3.67 IPS |
|
Pose Estimation (F16)
|
100% |
24534
29.7 IPS |
|
Pose Estimation (I8)
|
100% |
24629
29.8 IPS |
|
Object Detection (F32)
|
100% |
871
65.0 IPS |
|
Object Detection (F16)
|
100% |
1169
87.3 IPS |
|
Object Detection (I8)
|
97% |
884
66.0 IPS |
|
Face Detection (F32)
|
100% |
3444
41.0 IPS |
|
Face Detection (F16)
|
97% |
4153
49.4 IPS |
|
Face Detection (I8)
|
96% |
4129
49.1 IPS |
|
Depth Estimation (F32)
|
100% |
3210
24.9 IPS |
|
Depth Estimation (F16)
|
100% |
20590
159.7 IPS |
|
Depth Estimation (I8)
|
99% |
21720
168.4 IPS |
|
Style Transfer (F32)
|
24% |
8718
11.5 IPS |
|
Style Transfer (F16)
|
30% |
12474
16.4 IPS |
|
Style Transfer (I8)
|
30% |
12497
16.4 IPS |
|
Image Super-Resolution (F32)
|
100% |
1620
57.8 IPS |
|
Image Super-Resolution (F16)
|
100% |
3774
134.8 IPS |
|
Image Super-Resolution (I8)
|
100% |
3731
133.2 IPS |
|
Text Classification (F32)
|
100% |
211
303.6 IPS |
|
Text Classification (F16)
|
100% |
254
365.0 IPS |
|
Text Classification (I8)
|
96% |
251
360.6 IPS |
|
Machine Translation (F32)
|
100% |
361
6.65 IPS |
|
Machine Translation (F16)
|
100% |
355
6.53 IPS |
|
Machine Translation (I8)
|
99% |
360
6.62 IPS |