User | karen_he |
Upload Date | June 11 2024 07:10 PM |
Views | 2 |
System Information | |
---|---|
Operating System | iOS 17.5.1 |
Model | iPad16,6 |
Model ID | iPad16,6 |
Motherboard | J721AP |
CPU Information | |
---|---|
Name | ARM |
Topology | 1 Processor, 10 Cores |
Identifier | ARM |
Base Frequency | 4.44 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 6 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 | 15.05 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
4246
794.5 IPS |
|
Image Classification (F16)
|
100% |
4617
864.0 IPS |
|
Image Classification (I8)
|
99% |
4092
765.8 IPS |
|
Image Segmentation (F32)
|
100% |
1955
32.6 IPS |
|
Image Segmentation (F16)
|
100% |
2164
36.1 IPS |
|
Image Segmentation (I8)
|
100% |
2234
37.3 IPS |
|
Pose Estimation (F32)
|
100% |
27280
33.0 IPS |
|
Pose Estimation (F16)
|
100% |
28675
34.7 IPS |
|
Pose Estimation (I8)
|
100% |
28292
34.3 IPS |
|
Object Detection (F32)
|
100% |
3569
266.4 IPS |
|
Object Detection (F16)
|
100% |
3848
287.3 IPS |
|
Object Detection (I8)
|
97% |
2305
172.1 IPS |
|
Face Detection (F32)
|
100% |
9797
116.5 IPS |
|
Face Detection (F16)
|
98% |
14129
168.0 IPS |
|
Face Detection (I8)
|
97% |
13724
163.2 IPS |
|
Depth Estimation (F32)
|
100% |
19651
152.4 IPS |
|
Depth Estimation (F16)
|
100% |
21915
169.9 IPS |
|
Depth Estimation (I8)
|
37% |
13377
103.7 IPS |
|
Style Transfer (F32)
|
100% |
55332
72.8 IPS |
|
Style Transfer (F16)
|
100% |
65634
86.3 IPS |
|
Style Transfer (I8)
|
100% |
64972
85.5 IPS |
|
Image Super-Resolution (F32)
|
100% |
12076
431.3 IPS |
|
Image Super-Resolution (F16)
|
100% |
13441
480.0 IPS |
|
Image Super-Resolution (I8)
|
100% |
12610
450.3 IPS |
|
Text Classification (F32)
|
100% |
744
1.07 KIPS |
|
Text Classification (F16)
|
100% |
809
1.16 KIPS |
|
Text Classification (I8)
|
96% |
929
1.33 KIPS |
|
Machine Translation (F32)
|
100% |
1084
19.9 IPS |
|
Machine Translation (F16)
|
100% |
1047
19.3 IPS |
|
Machine Translation (I8)
|
99% |
973
17.9 IPS |