Upload Date | September 09 2024 09:12 AM |
Views | 1 |
System Information | |
---|---|
Operating System | iOS 18.1 |
Model | iPad Pro (11-inch, 4th generation) |
Model ID | iPad14,3 |
Motherboard | J617AP |
CPU Information | |
---|---|
Name | Apple M2 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM |
Base Frequency | 3.49 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
L1 Instruction Cache | 128 KB x 1 |
L1 Data Cache | 64.0 KB x 1 |
L2 Cache | 4.00 MB x 1 |
Memory Information | |
---|---|
Size | 7.37 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
1384
258.9 IPS |
|
Image Classification (F16)
|
100% |
2510
469.6 IPS |
|
Image Classification (I8)
|
99% |
2511
470.0 IPS |
|
Image Segmentation (F32)
|
100% |
855
14.3 IPS |
|
Image Segmentation (F16)
|
100% |
1134
18.9 IPS |
|
Image Segmentation (I8)
|
100% |
1119
18.7 IPS |
|
Pose Estimation (F32)
|
100% |
6622
8.02 IPS |
|
Pose Estimation (F16)
|
100% |
14183
17.2 IPS |
|
Pose Estimation (I8)
|
100% |
14147
17.1 IPS |
|
Object Detection (F32)
|
100% |
1449
108.2 IPS |
|
Object Detection (F16)
|
100% |
2449
182.8 IPS |
|
Object Detection (I8)
|
97% |
1446
108.0 IPS |
|
Face Detection (F32)
|
100% |
3085
36.7 IPS |
|
Face Detection (F16)
|
97% |
5973
71.0 IPS |
|
Face Detection (I8)
|
97% |
5958
70.8 IPS |
|
Depth Estimation (F32)
|
100% |
5674
44.0 IPS |
|
Depth Estimation (F16)
|
100% |
11613
90.1 IPS |
|
Depth Estimation (I8)
|
99% |
11723
90.9 IPS |
|
Style Transfer (F32)
|
100% |
18454
24.3 IPS |
|
Style Transfer (F16)
|
100% |
27778
36.5 IPS |
|
Style Transfer (I8)
|
100% |
28170
37.1 IPS |
|
Image Super-Resolution (F32)
|
100% |
4159
148.5 IPS |
|
Image Super-Resolution (F16)
|
100% |
4989
178.2 IPS |
|
Image Super-Resolution (I8)
|
100% |
4954
176.9 IPS |
|
Text Classification (F32)
|
100% |
2086
3.00 KIPS |
|
Text Classification (F16)
|
100% |
3422
4.92 KIPS |
|
Text Classification (I8)
|
96% |
3469
4.99 KIPS |
|
Machine Translation (F32)
|
100% |
1372
25.2 IPS |
|
Machine Translation (F16)
|
100% |
1625
29.9 IPS |
|
Machine Translation (I8)
|
99% |
1370
25.2 IPS |