Upload Date | May 08 2024 10:04 PM |
Views | 3 |
System Information | |
---|---|
Operating System | iOS 17.4.1 |
Model | iPad Pro 12.9-inch (4th generation) |
Model ID | iPad8,11 |
Motherboard | J420AP |
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 | 5.53 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
725
135.7 IPS |
|
Image Classification (F16)
|
100% |
2415
452.0 IPS |
|
Image Classification (I8)
|
99% |
2429
454.5 IPS |
|
Image Segmentation (F32)
|
100% |
260
4.33 IPS |
|
Image Segmentation (F16)
|
100% |
267
4.46 IPS |
|
Image Segmentation (I8)
|
100% |
262
4.38 IPS |
|
Pose Estimation (F32)
|
100% |
3044
3.69 IPS |
|
Pose Estimation (F16)
|
100% |
24931
30.2 IPS |
|
Pose Estimation (I8)
|
100% |
24864
30.1 IPS |
|
Object Detection (F32)
|
100% |
923
68.9 IPS |
|
Object Detection (F16)
|
100% |
1194
89.1 IPS |
|
Object Detection (I8)
|
97% |
927
69.2 IPS |
|
Face Detection (F32)
|
100% |
3470
41.3 IPS |
|
Face Detection (F16)
|
98% |
4379
52.1 IPS |
|
Face Detection (I8)
|
97% |
4356
51.8 IPS |
|
Depth Estimation (F32)
|
100% |
3299
25.6 IPS |
|
Depth Estimation (F16)
|
100% |
21949
170.2 IPS |
|
Depth Estimation (I8)
|
99% |
21350
165.6 IPS |
|
Style Transfer (F32)
|
100% |
8505
11.2 IPS |
|
Style Transfer (F16)
|
0
|
||
Style Transfer (I8)
|
100% |
10747
14.1 IPS |
|
Image Super-Resolution (F32)
|
100% |
1759
62.8 IPS |
|
Image Super-Resolution (F16)
|
100% |
3942
140.8 IPS |
|
Image Super-Resolution (I8)
|
100% |
3998
142.8 IPS |
|
Text Classification (F32)
|
100% |
174
250.7 IPS |
|
Text Classification (F16)
|
100% |
274
393.1 IPS |
|
Text Classification (I8)
|
96% |
442
635.5 IPS |
|
Machine Translation (F32)
|
100% |
346
6.37 IPS |
|
Machine Translation (F16)
|
100% |
336
6.19 IPS |
|
Machine Translation (I8)
|
99% |
330
6.07 IPS |