iPad mini 4
Geekbench ML Score
276
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64
Result Information
| Upload Date | July 22 2021 09:31 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | iOS 14.7 |
| Model | iPad mini 4 |
| Model ID | iPad5,1 |
| Motherboard | J96AP |
| CPU Information | |
|---|---|
| Name | Apple A8 |
| Topology | 1 Processor, 2 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 | 1.00 MB x 1 |
| Memory Information | |
|---|---|
| Size | 1.94 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
305
32.7 IPS |
|
|
Image Classification (F16)
|
100% |
431
46.2 IPS |
|
|
Image Classification (I8)
|
81% |
143
15.3 IPS |
|
|
Image Segmentation (F32)
|
100% |
494
3.05 IPS |
|
|
Image Segmentation (F16)
|
100% |
653
4.04 IPS |
|
|
Image Segmentation (I8)
|
89% |
245
1.51 IPS |
|
|
Pose Estimation (F32)
|
100% |
179
0.73 IPS |
|
|
Pose Estimation (F16)
|
100% |
303
1.22 IPS |
|
|
Pose Estimation (I8)
|
80% |
47
0.19 IPS |
|
|
Object Detection (F32)
|
100% |
397
13.9 IPS |
|
|
Object Detection (F16)
|
100% |
548
19.2 IPS |
|
|
Object Detection (I8)
|
52% |
193
6.77 IPS |
|
|
Face Detection (F32)
|
100% |
500
5.74 IPS |
|
|
Face Detection (F16)
|
97% |
765
8.79 IPS |
|
|
Face Detection (I8)
|
75% |
180
2.06 IPS |
|
|
Text Classification (F32)
|
100% |
239
94.6 IPS |
|
|
Text Classification (F16)
|
98% |
303
120.0 IPS |
|
|
Machine Translation (F32)
|
100% |
176
27.2 IPS |
|
|
Machine Translation (F16)
|
100% |
177
27.2 IPS |
