Upload Date | September 20 2024 07:10 AM |
Views | 2 |
System Information | |
---|---|
Operating System | iOS 18.0 |
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% |
1374
257.1 IPS |
|
Image Classification (F16)
|
100% |
2505
468.7 IPS |
|
Image Classification (I8)
|
99% |
2515
470.7 IPS |
|
Image Segmentation (F32)
|
100% |
862
14.4 IPS |
|
Image Segmentation (F16)
|
100% |
1124
18.8 IPS |
|
Image Segmentation (I8)
|
100% |
1125
18.8 IPS |
|
Pose Estimation (F32)
|
100% |
6639
8.04 IPS |
|
Pose Estimation (F16)
|
100% |
14178
17.2 IPS |
|
Pose Estimation (I8)
|
100% |
14277
17.3 IPS |
|
Object Detection (F32)
|
100% |
1458
108.9 IPS |
|
Object Detection (F16)
|
100% |
2449
182.9 IPS |
|
Object Detection (I8)
|
97% |
1459
108.9 IPS |
|
Face Detection (F32)
|
100% |
3080
36.6 IPS |
|
Face Detection (F16)
|
97% |
5938
70.6 IPS |
|
Face Detection (I8)
|
97% |
5976
71.1 IPS |
|
Depth Estimation (F32)
|
100% |
5679
44.0 IPS |
|
Depth Estimation (F16)
|
100% |
11716
90.9 IPS |
|
Depth Estimation (I8)
|
99% |
11785
91.4 IPS |
|
Style Transfer (F32)
|
100% |
18490
24.3 IPS |
|
Style Transfer (F16)
|
100% |
27922
36.7 IPS |
|
Style Transfer (I8)
|
100% |
27958
36.8 IPS |
|
Image Super-Resolution (F32)
|
100% |
4182
149.3 IPS |
|
Image Super-Resolution (F16)
|
100% |
5020
179.3 IPS |
|
Image Super-Resolution (I8)
|
100% |
4952
176.8 IPS |
|
Text Classification (F32)
|
100% |
2037
2.93 KIPS |
|
Text Classification (F16)
|
100% |
3387
4.87 KIPS |
|
Text Classification (I8)
|
96% |
3376
4.85 KIPS |
|
Machine Translation (F32)
|
100% |
1373
25.3 IPS |
|
Machine Translation (F16)
|
100% |
1616
29.7 IPS |
|
Machine Translation (I8)
|
99% |
1375
25.3 IPS |