Upload Date | May 08 2024 03:34 PM |
Views | 1 |
System Information | |
---|---|
Operating System | iOS 17.4.1 |
Model | iPad Pro (12.9-inch 5th generation) |
Model ID | iPad13,10 |
Motherboard | J523AP |
CPU Information | |
---|---|
Name | Apple M1 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM |
Base Frequency | 3.19 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 | 7.31 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
2595
485.5 IPS |
|
Image Classification (F16)
|
100% |
1877
351.3 IPS |
|
Image Classification (I8)
|
99% |
1853
346.7 IPS |
|
Image Segmentation (F32)
|
100% |
833
13.9 IPS |
|
Image Segmentation (F16)
|
100% |
878
14.7 IPS |
|
Image Segmentation (I8)
|
100% |
898
15.0 IPS |
|
Pose Estimation (F32)
|
100% |
16604
20.1 IPS |
|
Pose Estimation (F16)
|
100% |
18284
22.1 IPS |
|
Pose Estimation (I8)
|
100% |
17983
21.8 IPS |
|
Object Detection (F32)
|
100% |
1505
112.3 IPS |
|
Object Detection (F16)
|
100% |
2014
150.3 IPS |
|
Object Detection (I8)
|
97% |
1502
112.1 IPS |
|
Face Detection (F32)
|
100% |
5935
70.6 IPS |
|
Face Detection (F16)
|
98% |
7207
85.7 IPS |
|
Face Detection (I8)
|
97% |
7569
90.0 IPS |
|
Depth Estimation (F32)
|
100% |
12704
98.5 IPS |
|
Depth Estimation (F16)
|
100% |
13764
106.7 IPS |
|
Depth Estimation (I8)
|
37% |
12682
98.4 IPS |
|
Style Transfer (F32)
|
100% |
28645
37.7 IPS |
|
Style Transfer (F16)
|
100% |
30540
40.2 IPS |
|
Style Transfer (I8)
|
100% |
29685
39.0 IPS |
|
Image Super-Resolution (F32)
|
100% |
5677
202.7 IPS |
|
Image Super-Resolution (F16)
|
100% |
5626
200.9 IPS |
|
Image Super-Resolution (I8)
|
100% |
5874
209.8 IPS |
|
Text Classification (F32)
|
100% |
1088
1.56 KIPS |
|
Text Classification (F16)
|
100% |
767
1.10 KIPS |
|
Text Classification (I8)
|
96% |
715
1.03 KIPS |
|
Machine Translation (F32)
|
100% |
608
11.2 IPS |
|
Machine Translation (F16)
|
100% |
631
11.6 IPS |
|
Machine Translation (I8)
|
99% |
536
9.87 IPS |