Upload Date | July 26 2024 05:47 PM |
Views | 1 |
System Information | |
---|---|
Operating System | iOS 17.5.1 |
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 | 15.31 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
1706
319.3 IPS |
|
Image Classification (F16)
|
100% |
1187
222.1 IPS |
|
Image Classification (I8)
|
99% |
1198
224.2 IPS |
|
Image Segmentation (F32)
|
100% |
820
13.7 IPS |
|
Image Segmentation (F16)
|
100% |
869
14.5 IPS |
|
Image Segmentation (I8)
|
100% |
844
14.1 IPS |
|
Pose Estimation (F32)
|
100% |
15949
19.3 IPS |
|
Pose Estimation (F16)
|
100% |
17978
21.8 IPS |
|
Pose Estimation (I8)
|
100% |
17575
21.3 IPS |
|
Object Detection (F32)
|
100% |
1525
113.9 IPS |
|
Object Detection (F16)
|
100% |
1470
109.7 IPS |
|
Object Detection (I8)
|
97% |
1495
111.6 IPS |
|
Face Detection (F32)
|
100% |
5772
68.6 IPS |
|
Face Detection (F16)
|
98% |
7256
86.3 IPS |
|
Face Detection (I8)
|
97% |
7107
84.5 IPS |
|
Depth Estimation (F32)
|
100% |
11832
91.8 IPS |
|
Depth Estimation (F16)
|
100% |
13596
105.4 IPS |
|
Depth Estimation (I8)
|
37% |
12479
96.8 IPS |
|
Style Transfer (F32)
|
100% |
27298
35.9 IPS |
|
Style Transfer (F16)
|
100% |
30839
40.6 IPS |
|
Style Transfer (I8)
|
100% |
31804
41.8 IPS |
|
Image Super-Resolution (F32)
|
100% |
4746
169.5 IPS |
|
Image Super-Resolution (F16)
|
100% |
4991
178.2 IPS |
|
Image Super-Resolution (I8)
|
100% |
5823
208.0 IPS |
|
Text Classification (F32)
|
100% |
1171
1.68 KIPS |
|
Text Classification (F16)
|
100% |
765
1.10 KIPS |
|
Text Classification (I8)
|
96% |
763
1.10 KIPS |
|
Machine Translation (F32)
|
100% |
532
9.79 IPS |
|
Machine Translation (F16)
|
100% |
540
9.93 IPS |
|
Machine Translation (I8)
|
99% |
543
9.99 IPS |