iPad Air 2
Geekbench ML Score
256
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64
Result Information
| User | plusterkopp |
| Upload Date | January 08 2024 06:11 PM |
| Views | 3 |
System Information
| System Information | |
|---|---|
| Operating System | iOS 15.8 |
| Model | iPad Air 2 |
| Model ID | iPad5,4 |
| Motherboard | J82AP |
| CPU Information | |
|---|---|
| Name | Apple A8X |
| Topology | 1 Processor, 3 Cores |
| Identifier | ARM |
| Base Frequency | 1.50 GHz |
| L1 Instruction Cache | 64.0 KB x 1 |
| L1 Data Cache | 64.0 KB x 1 |
| L2 Cache | 2.00 MB x 1 |
| Memory Information | |
|---|---|
| Size | 1.94 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
162
17.4 IPS |
|
|
Image Classification (F16)
|
100% |
166
17.8 IPS |
|
|
Image Classification (I8)
|
81% |
349
37.4 IPS |
|
|
Image Segmentation (F32)
|
100% |
302
1.86 IPS |
|
|
Image Segmentation (F16)
|
100% |
301
1.86 IPS |
|
|
Image Segmentation (I8)
|
89% |
675
4.17 IPS |
|
|
Pose Estimation (F32)
|
100% |
113
0.46 IPS |
|
|
Pose Estimation (F16)
|
100% |
113
0.46 IPS |
|
|
Pose Estimation (I8)
|
80% |
143
0.58 IPS |
|
|
Object Detection (F32)
|
100% |
281
9.86 IPS |
|
|
Object Detection (F16)
|
100% |
286
10.1 IPS |
|
|
Object Detection (I8)
|
52% |
508
17.8 IPS |
|
|
Face Detection (F32)
|
100% |
355
4.08 IPS |
|
|
Face Detection (F16)
|
100% |
354
4.07 IPS |
|
|
Face Detection (I8)
|
75% |
496
5.69 IPS |
|
|
Text Classification (F32)
|
100% |
221
87.3 IPS |
|
|
Text Classification (F16)
|
100% |
215
85.0 IPS |
|
|
Machine Translation (F32)
|
100% |
214
32.9 IPS |
|
|
Machine Translation (F16)
|
100% |
214
33.0 IPS |
