| User | andremachado |
| Upload Date | September 11 2024 10:56 PM |
| Views | 10 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A10X Fusion |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| Model | iPad Pro (10.5-inch) |
| Model ID | iPad7,3 |
| Motherboard | J207AP |
| CPU Information | |
|---|---|
| Name | Apple A10X Fusion |
| Topology | 1 Processor, 3 Cores |
| Identifier | ARM |
| Base Frequency | 2.34 GHz |
| Cluster 1 | 3 Cores |
| Memory Information | |
|---|---|
| Size | 3.91 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
245
45.6 IPS |
|
|
Image Classification (HP)
|
100% |
218
40.5 IPS |
|
|
Image Classification (Q)
|
96% |
116
21.7 IPS |
|
|
Image Segmentation (SP)
|
100% |
200
3.24 IPS |
|
|
Image Segmentation (HP)
|
100% |
199
3.22 IPS |
|
|
Image Segmentation (Q)
|
99% |
157
2.54 IPS |
|
|
Pose Estimation (SP)
|
100% |
1535
1.79 IPS |
|
|
Pose Estimation (HP)
|
100% |
1243
1.45 IPS |
|
|
Pose Estimation (Q)
|
95% |
894
1.05 IPS |
|
|
Object Detection (SP)
|
100% |
239
18.9 IPS |
|
|
Object Detection (HP)
|
100% |
213
16.9 IPS |
|
|
Object Detection (Q)
|
92% |
126
10.0 IPS |
|
|
Face Detection (SP)
|
100% |
519
6.16 IPS |
|
|
Face Detection (HP)
|
100% |
522
6.20 IPS |
|
|
Face Detection (Q)
|
100% |
210
2.50 IPS |
|
|
Depth Estimation (SP)
|
100% |
684
5.27 IPS |
|
|
Depth Estimation (HP)
|
99% |
624
4.80 IPS |
|
|
Depth Estimation (Q)
|
86% |
398
3.10 IPS |
|
|
Style Transfer (SP)
|
100% |
2155
2.77 IPS |
|
|
Style Transfer (HP)
|
100% |
2012
2.59 IPS |
|
|
Style Transfer (Q)
|
96% |
1427
1.84 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
591
21.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
585
21.6 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
276
10.2 IPS |
|
|
Text Classification (SP)
|
100% |
159
212.8 IPS |
|
|
Text Classification (HP)
|
100% |
134
178.9 IPS |
|
|
Text Classification (Q)
|
93% |
135
181.2 IPS |
|
|
Machine Translation (SP)
|
100% |
351
6.04 IPS |
|
|
Machine Translation (HP)
|
100% |
281
4.84 IPS |
|
|
Machine Translation (Q)
|
98% |
280
4.83 IPS |