Upload Date | August 16 2024 03:15 PM |
Views | 2 |
System Information | |
---|---|
Operating System | iOS 16.6 |
Model | iPad Air (5th generation) |
Model ID | iPad13,16 |
Motherboard | J407AP |
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 | 7.47 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
1711
320.2 IPS |
|
Image Classification (F16)
|
100% |
1840
344.3 IPS |
|
Image Classification (I8)
|
99% |
1929
360.9 IPS |
|
Image Segmentation (F32)
|
100% |
519
8.67 IPS |
|
Image Segmentation (F16)
|
100% |
506
8.45 IPS |
|
Image Segmentation (I8)
|
100% |
497
8.30 IPS |
|
Pose Estimation (F32)
|
100% |
14310
17.3 IPS |
|
Pose Estimation (F16)
|
100% |
16026
19.4 IPS |
|
Pose Estimation (I8)
|
100% |
12537
15.2 IPS |
|
Object Detection (F32)
|
100% |
1437
107.3 IPS |
|
Object Detection (F16)
|
100% |
1455
108.6 IPS |
|
Object Detection (I8)
|
97% |
1494
111.5 IPS |
|
Face Detection (F32)
|
100% |
5136
61.1 IPS |
|
Face Detection (F16)
|
97% |
5728
68.1 IPS |
|
Face Detection (I8)
|
96% |
5892
70.1 IPS |
|
Depth Estimation (F32)
|
100% |
9944
77.1 IPS |
|
Depth Estimation (F16)
|
100% |
10531
81.7 IPS |
|
Depth Estimation (I8)
|
99% |
11774
91.3 IPS |
|
Style Transfer (F32)
|
100% |
24331
32.0 IPS |
|
Style Transfer (F16)
|
100% |
28902
38.0 IPS |
|
Style Transfer (I8)
|
100% |
29218
38.4 IPS |
|
Image Super-Resolution (F32)
|
100% |
4442
158.6 IPS |
|
Image Super-Resolution (F16)
|
100% |
5036
179.9 IPS |
|
Image Super-Resolution (I8)
|
100% |
5850
208.9 IPS |
|
Text Classification (F32)
|
100% |
460
661.5 IPS |
|
Text Classification (F16)
|
100% |
454
652.3 IPS |
|
Text Classification (I8)
|
96% |
432
620.8 IPS |
|
Machine Translation (F32)
|
100% |
961
17.7 IPS |
|
Machine Translation (F16)
|
100% |
1009
18.6 IPS |
|
Machine Translation (I8)
|
99% |
973
17.9 IPS |