iPad Pro (9.7-inch)
Geekbench ML Score
686
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64
Result Information
| User | livetolove6416 |
| Upload Date | June 12 2021 10:26 PM |
| Views | 3 |
System Information
| System Information | |
|---|---|
| Operating System | iOS 14.6 |
| 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 | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
564
60.4 IPS |
|
|
Image Classification (F16)
|
100% |
845
90.5 IPS |
|
|
Image Classification (I8)
|
81% |
235
25.1 IPS |
|
|
Image Segmentation (F32)
|
100% |
1908
11.8 IPS |
|
|
Image Segmentation (F16)
|
100% |
3180
19.6 IPS |
|
|
Image Segmentation (I8)
|
89% |
437
2.70 IPS |
|
|
Pose Estimation (F32)
|
100% |
486
1.97 IPS |
|
|
Pose Estimation (F16)
|
100% |
1462
5.91 IPS |
|
|
Pose Estimation (I8)
|
80% |
82
0.33 IPS |
|
|
Object Detection (F32)
|
100% |
1035
36.3 IPS |
|
|
Object Detection (F16)
|
100% |
1111
39.0 IPS |
|
|
Object Detection (I8)
|
52% |
334
11.7 IPS |
|
|
Face Detection (F32)
|
100% |
1685
19.4 IPS |
|
|
Face Detection (F16)
|
97% |
3217
37.0 IPS |
|
|
Face Detection (I8)
|
75% |
325
3.74 IPS |
|
|
Text Classification (F32)
|
100% |
471
186.3 IPS |
|
|
Text Classification (F16)
|
98% |
594
235.1 IPS |
|
|
Machine Translation (F32)
|
100% |
478
73.7 IPS |
|
|
Machine Translation (F16)
|
100% |
497
76.5 IPS |
