Upload Date | June 11 2024 07:03 PM |
Views | 2 |
System Information | |
---|---|
Operating System | iOS 17.5.1 |
Model | iPad Pro 12.9-inch (4th generation) |
Model ID | iPad8,12 |
Motherboard | J421AP |
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% |
916
171.3 IPS |
|
Image Classification (F16)
|
100% |
2270
424.7 IPS |
|
Image Classification (I8)
|
99% |
2309
432.1 IPS |
|
Image Segmentation (F32)
|
100% |
250
4.18 IPS |
|
Image Segmentation (F16)
|
100% |
258
4.31 IPS |
|
Image Segmentation (I8)
|
100% |
258
4.31 IPS |
|
Pose Estimation (F32)
|
100% |
3007
3.64 IPS |
|
Pose Estimation (F16)
|
100% |
24992
30.3 IPS |
|
Pose Estimation (I8)
|
100% |
25169
30.5 IPS |
|
Object Detection (F32)
|
100% |
895
66.8 IPS |
|
Object Detection (F16)
|
100% |
1190
88.8 IPS |
|
Object Detection (I8)
|
97% |
895
66.8 IPS |
|
Face Detection (F32)
|
100% |
3478
41.4 IPS |
|
Face Detection (F16)
|
98% |
4361
51.9 IPS |
|
Face Detection (I8)
|
97% |
4296
51.1 IPS |
|
Depth Estimation (F32)
|
100% |
3314
25.7 IPS |
|
Depth Estimation (F16)
|
100% |
20742
160.9 IPS |
|
Depth Estimation (I8)
|
99% |
20607
159.8 IPS |
|
Style Transfer (F32)
|
100% |
8537
11.2 IPS |
|
Style Transfer (F16)
|
100% |
10381
13.7 IPS |
|
Style Transfer (I8)
|
100% |
10416
13.7 IPS |
|
Image Super-Resolution (F32)
|
100% |
1715
61.3 IPS |
|
Image Super-Resolution (F16)
|
100% |
3746
133.8 IPS |
|
Image Super-Resolution (I8)
|
100% |
3729
133.2 IPS |
|
Text Classification (F32)
|
100% |
209
300.4 IPS |
|
Text Classification (F16)
|
100% |
251
360.2 IPS |
|
Text Classification (I8)
|
96% |
251
361.3 IPS |
|
Machine Translation (F32)
|
100% |
363
6.68 IPS |
|
Machine Translation (F16)
|
100% |
357
6.56 IPS |
|
Machine Translation (I8)
|
99% |
363
6.67 IPS |