Upload Date | August 15 2024 04:27 PM |
Views | 1 |
System Information | |
---|---|
Operating System | iOS 18.0 |
Model | iPad Pro (12.9-inch 5th generation) |
Model ID | iPad13,11 |
Motherboard | J523xAP |
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 | 15.35 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
1366
255.7 IPS |
|
Image Classification (F16)
|
100% |
1449
271.2 IPS |
|
Image Classification (I8)
|
99% |
1482
277.4 IPS |
|
Image Segmentation (F32)
|
100% |
789
13.2 IPS |
|
Image Segmentation (F16)
|
100% |
832
13.9 IPS |
|
Image Segmentation (I8)
|
100% |
826
13.8 IPS |
|
Pose Estimation (F32)
|
100% |
16367
19.8 IPS |
|
Pose Estimation (F16)
|
100% |
18091
21.9 IPS |
|
Pose Estimation (I8)
|
100% |
17665
21.4 IPS |
|
Object Detection (F32)
|
100% |
1460
109.0 IPS |
|
Object Detection (F16)
|
100% |
1408
105.1 IPS |
|
Object Detection (I8)
|
97% |
1425
106.4 IPS |
|
Face Detection (F32)
|
100% |
5889
70.0 IPS |
|
Face Detection (F16)
|
98% |
7229
86.0 IPS |
|
Face Detection (I8)
|
97% |
7380
87.7 IPS |
|
Depth Estimation (F32)
|
100% |
12078
93.7 IPS |
|
Depth Estimation (F16)
|
100% |
13625
105.7 IPS |
|
Depth Estimation (I8)
|
99% |
12490
96.9 IPS |
|
Style Transfer (F32)
|
100% |
27346
36.0 IPS |
|
Style Transfer (F16)
|
100% |
31055
40.8 IPS |
|
Style Transfer (I8)
|
100% |
34480
45.4 IPS |
|
Image Super-Resolution (F32)
|
100% |
5121
182.9 IPS |
|
Image Super-Resolution (F16)
|
100% |
6321
225.7 IPS |
|
Image Super-Resolution (I8)
|
100% |
5880
210.0 IPS |
|
Text Classification (F32)
|
100% |
2132
3.06 KIPS |
|
Text Classification (F16)
|
100% |
3695
5.31 KIPS |
|
Text Classification (I8)
|
96% |
3708
5.33 KIPS |
|
Machine Translation (F32)
|
100% |
496
9.12 IPS |
|
Machine Translation (F16)
|
100% |
486
8.95 IPS |
|
Machine Translation (I8)
|
99% |
504
9.28 IPS |