User | Xabla |
Upload Date | October 09 2024 05:21 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A12Z Bionic |
System Information | |
---|---|
Operating System | iOS 18.0 |
Model | iPad Pro 12.9-inch (4th generation) |
Model ID | iPad8,11 |
Motherboard | J420AP |
CPU Information | |
---|---|
Name | Apple A12Z Bionic |
Topology | 1 Processor, 8 Cores |
Identifier | ARM |
Base Frequency | 2.49 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 5.53 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
180
33.5 IPS |
|
Image Classification (HP)
|
100% |
1935
359.8 IPS |
|
Image Classification (Q)
|
99% |
121
22.6 IPS |
|
Image Segmentation (SP)
|
100% |
171
2.77 IPS |
|
Image Segmentation (HP)
|
100% |
300
4.86 IPS |
|
Image Segmentation (Q)
|
99% |
133
2.15 IPS |
|
Pose Estimation (SP)
|
100% |
667
0.78 IPS |
|
Pose Estimation (HP)
|
100% |
16295
19.0 IPS |
|
Pose Estimation (Q)
|
95% |
582
0.68 IPS |
|
Object Detection (SP)
|
100% |
191
15.1 IPS |
|
Object Detection (HP)
|
100% |
1122
89.0 IPS |
|
Object Detection (Q)
|
94% |
143
11.4 IPS |
|
Face Detection (SP)
|
100% |
495
5.88 IPS |
|
Face Detection (HP)
|
100% |
4919
58.4 IPS |
|
Face Detection (Q)
|
100% |
194
2.30 IPS |
|
Depth Estimation (SP)
|
100% |
495
3.81 IPS |
|
Depth Estimation (HP)
|
99% |
16342
125.9 IPS |
|
Depth Estimation (Q)
|
86% |
331
2.59 IPS |
|
Style Transfer (SP)
|
100% |
1280
1.65 IPS |
|
Style Transfer (HP)
|
100% |
1268
1.63 IPS |
|
Style Transfer (Q)
|
96% |
1061
1.37 IPS |
|
Image Super-Resolution (SP)
|
100% |
387
14.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
2557
94.4 IPS |
|
Image Super-Resolution (Q)
|
99% |
336
12.4 IPS |
|
Text Classification (SP)
|
100% |
157
209.7 IPS |
|
Text Classification (HP)
|
100% |
201
268.1 IPS |
|
Text Classification (Q)
|
93% |
201
269.2 IPS |
|
Machine Translation (SP)
|
100% |
316
5.44 IPS |
|
Machine Translation (HP)
|
100% |
248
4.28 IPS |
|
Machine Translation (Q)
|
98% |
248
4.28 IPS |