Upload Date | May 16 2022 03:11 AM |
Views | 1 |
System Information | |
---|---|
Operating System | iOS 15.5 |
Model | iPad Pro (12.9-inch 5th generation) |
Model ID | iPad13,8 |
Motherboard | J522AP |
CPU Information | |
---|---|
Name | Apple M1 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM |
Base Frequency | 3.19 GHz |
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 | 7.31 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
4226
452.8 IPS |
|
Image Classification (F16)
|
100% |
5911
633.3 IPS |
|
Image Classification (I8)
|
81% |
676
72.4 IPS |
|
Image Segmentation (F32)
|
100% |
8143
50.3 IPS |
|
Image Segmentation (F16)
|
100% |
11874
73.3 IPS |
|
Image Segmentation (I8)
|
89% |
1234
7.62 IPS |
|
Pose Estimation (F32)
|
100% |
2869
11.6 IPS |
|
Pose Estimation (F16)
|
100% |
6854
27.7 IPS |
|
Pose Estimation (I8)
|
80% |
236
0.96 IPS |
|
Object Detection (F32)
|
100% |
3903
137.0 IPS |
|
Object Detection (F16)
|
100% |
3940
138.3 IPS |
|
Object Detection (I8)
|
52% |
969
34.0 IPS |
|
Face Detection (F32)
|
100% |
7108
81.7 IPS |
|
Face Detection (F16)
|
97% |
12472
143.3 IPS |
|
Face Detection (I8)
|
75% |
949
10.9 IPS |
|
Text Classification (F32)
|
100% |
3395
1.34 KIPS |
|
Text Classification (F16)
|
100% |
3740
1.48 KIPS |
|
Machine Translation (F32)
|
100% |
1852
285.4 IPS |
|
Machine Translation (F16)
|
100% |
1860
286.7 IPS |