| User | ju83 |
| Upload Date | October 06 2024 06:05 AM |
| Views | 14 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.0 |
| Model | iPad Air (3rd generation) |
| Model ID | iPad11,3 |
| Motherboard | J217AP |
| CPU Information | |
|---|---|
| Name | Apple A12 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.49 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 2.84 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
294
54.8 IPS |
|
|
Image Classification (HP)
|
100% |
262
48.7 IPS |
|
|
Image Classification (Q)
|
96% |
138
25.8 IPS |
|
|
Image Segmentation (SP)
|
100% |
217
3.51 IPS |
|
|
Image Segmentation (HP)
|
100% |
246
3.99 IPS |
|
|
Image Segmentation (Q)
|
99% |
178
2.88 IPS |
|
|
Pose Estimation (SP)
|
100% |
1631
1.90 IPS |
|
|
Pose Estimation (HP)
|
100% |
2335
2.72 IPS |
|
|
Pose Estimation (Q)
|
96% |
656
0.77 IPS |
|
|
Object Detection (SP)
|
100% |
532
42.2 IPS |
|
|
Object Detection (HP)
|
100% |
538
42.7 IPS |
|
|
Object Detection (Q)
|
92% |
159
12.7 IPS |
|
|
Face Detection (SP)
|
100% |
1901
22.6 IPS |
|
|
Face Detection (HP)
|
100% |
2196
26.1 IPS |
|
|
Face Detection (Q)
|
100% |
264
3.13 IPS |
|
|
Depth Estimation (SP)
|
100% |
1764
13.6 IPS |
|
|
Depth Estimation (HP)
|
99% |
2588
19.9 IPS |
|
|
Depth Estimation (Q)
|
86% |
416
3.25 IPS |
|
|
Style Transfer (SP)
|
100% |
4586
5.90 IPS |
|
|
Style Transfer (HP)
|
100% |
5596
7.19 IPS |
|
|
Style Transfer (Q)
|
96% |
1458
1.88 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
803
29.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1041
38.4 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
295
10.9 IPS |
|
|
Text Classification (SP)
|
100% |
148
198.0 IPS |
|
|
Text Classification (HP)
|
100% |
199
265.9 IPS |
|
|
Text Classification (Q)
|
93% |
201
269.8 IPS |
|
|
Machine Translation (SP)
|
100% |
180
3.10 IPS |
|
|
Machine Translation (HP)
|
100% |
158
2.72 IPS |
|
|
Machine Translation (Q)
|
98% |
158
2.74 IPS |