Upload Date | October 14 2021 06:19 AM |
Views | 1 |
System Information | |
---|---|
Operating System | iOS 14.8 |
Model | iPad Pro (9.7-inch) |
Model ID | iPad6,3 |
Motherboard | J127AP |
CPU Information | |
---|---|
Name | Apple A9X |
Topology | 1 Processor, 2 Cores |
Identifier | ARM |
Base Frequency | 2.26 GHz |
L1 Instruction Cache | 64.0 KB x 1 |
L1 Data Cache | 64.0 KB x 1 |
L2 Cache | 3.00 MB x 1 |
Memory Information | |
---|---|
Size | 1.92 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | Core ML |
Device |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
317
34.0 IPS |
|
Image Classification (F16)
|
100% |
287
30.8 IPS |
|
Image Classification (I8)
|
81% |
233
25.0 IPS |
|
Image Segmentation (F32)
|
100% |
636
3.93 IPS |
|
Image Segmentation (F16)
|
100% |
636
3.93 IPS |
|
Image Segmentation (I8)
|
89% |
436
2.69 IPS |
|
Pose Estimation (F32)
|
100% |
611
2.47 IPS |
|
Pose Estimation (F16)
|
100% |
620
2.51 IPS |
|
Pose Estimation (I8)
|
80% |
81
0.33 IPS |
|
Object Detection (F32)
|
100% |
569
20.0 IPS |
|
Object Detection (F16)
|
100% |
566
19.9 IPS |
|
Object Detection (I8)
|
52% |
333
11.7 IPS |
|
Face Detection (F32)
|
100% |
859
9.87 IPS |
|
Face Detection (F16)
|
100% |
874
10.0 IPS |
|
Face Detection (I8)
|
75% |
327
3.75 IPS |
|
Text Classification (F32)
|
98% |
82
32.5 IPS |
|
Text Classification (F16)
|
98% |
70
27.5 IPS |
|
Machine Translation (F32)
|
100% |
504
77.7 IPS |
|
Machine Translation (F16)
|
100% |
501
77.3 IPS |