Upload Date | May 09 2024 10:45 AM |
Views | 7 |
System Information | |
---|---|
Operating System | iOS 17.5 |
Model | iPad16,4 |
Model ID | iPad16,4 |
Motherboard | J718AP |
CPU Information | |
---|---|
Name | ARM |
Topology | 1 Processor, 10 Cores |
Identifier | ARM |
Base Frequency | 4.39 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 | 15.13 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
4260
797.2 IPS |
|
Image Classification (F16)
|
100% |
4561
853.6 IPS |
|
Image Classification (I8)
|
99% |
4166
779.6 IPS |
|
Image Segmentation (F32)
|
100% |
1978
33.0 IPS |
|
Image Segmentation (F16)
|
100% |
2192
36.6 IPS |
|
Image Segmentation (I8)
|
100% |
2213
37.0 IPS |
|
Pose Estimation (F32)
|
100% |
27198
32.9 IPS |
|
Pose Estimation (F16)
|
100% |
29009
35.1 IPS |
|
Pose Estimation (I8)
|
100% |
28289
34.3 IPS |
|
Object Detection (F32)
|
100% |
3674
274.3 IPS |
|
Object Detection (F16)
|
100% |
3946
294.6 IPS |
|
Object Detection (I8)
|
97% |
3337
249.1 IPS |
|
Face Detection (F32)
|
100% |
11457
136.2 IPS |
|
Face Detection (F16)
|
98% |
14218
169.1 IPS |
|
Face Detection (I8)
|
97% |
13730
163.3 IPS |
|
Depth Estimation (F32)
|
100% |
19962
154.8 IPS |
|
Depth Estimation (F16)
|
100% |
22272
172.7 IPS |
|
Depth Estimation (I8)
|
37% |
20258
157.1 IPS |
|
Style Transfer (F32)
|
100% |
55917
73.6 IPS |
|
Style Transfer (F16)
|
100% |
65736
86.5 IPS |
|
Style Transfer (I8)
|
100% |
65074
85.6 IPS |
|
Image Super-Resolution (F32)
|
100% |
8377
299.2 IPS |
|
Image Super-Resolution (F16)
|
100% |
9569
341.7 IPS |
|
Image Super-Resolution (I8)
|
100% |
9401
335.8 IPS |
|
Text Classification (F32)
|
100% |
1485
2.13 KIPS |
|
Text Classification (F16)
|
100% |
1568
2.25 KIPS |
|
Text Classification (I8)
|
96% |
1248
1.79 KIPS |
|
Machine Translation (F32)
|
100% |
1112
20.5 IPS |
|
Machine Translation (F16)
|
100% |
1170
21.5 IPS |
|
Machine Translation (I8)
|
99% |
917
16.9 IPS |