User | Stephen_L |
Upload Date | August 26 2024 10:44 AM |
Views | 3 |
System Information | |
---|---|
Operating System | iOS 16.7.8 |
Model | iPad Pro (12.9-inch) |
Model ID | iPad6,7 |
Motherboard | J98aAP |
CPU Information | |
---|---|
Name | Apple A9X |
Topology | 1 Processor, 2 Cores |
Identifier | ARM |
Base Frequency | 2.26 GHz |
Cluster 1 | 2 Cores |
L1 Instruction Cache | 64.0 KB x 1 |
L1 Data Cache | 64.0 KB x 1 |
L2 Cache | 3.00 MB x 1 |
Memory Information | |
---|---|
Size | 3.90 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
309
57.8 IPS |
|
Image Classification (F16)
|
100% |
293
54.9 IPS |
|
Image Classification (I8)
|
99% |
283
52.9 IPS |
|
Image Segmentation (F32)
|
100% |
185
3.08 IPS |
|
Image Segmentation (F16)
|
100% |
182
3.03 IPS |
|
Image Segmentation (I8)
|
100% |
185
3.10 IPS |
|
Pose Estimation (F32)
|
100% |
2022
2.45 IPS |
|
Pose Estimation (F16)
|
100% |
1994
2.42 IPS |
|
Pose Estimation (I8)
|
100% |
1991
2.41 IPS |
|
Object Detection (F32)
|
100% |
394
29.4 IPS |
|
Object Detection (F16)
|
100% |
367
27.4 IPS |
|
Object Detection (I8)
|
97% |
297
22.2 IPS |
|
Face Detection (F32)
|
100% |
1403
16.7 IPS |
|
Face Detection (F16)
|
100% |
1345
16.0 IPS |
|
Face Detection (I8)
|
99% |
1346
16.0 IPS |
|
Depth Estimation (F32)
|
100% |
2245
17.4 IPS |
|
Depth Estimation (F16)
|
100% |
2227
17.3 IPS |
|
Depth Estimation (I8)
|
99% |
2224
17.2 IPS |
|
Style Transfer (F32)
|
100% |
5571
7.33 IPS |
|
Style Transfer (F16)
|
100% |
5517
7.26 IPS |
|
Style Transfer (I8)
|
100% |
5523
7.26 IPS |
|
Image Super-Resolution (F32)
|
100% |
1112
39.7 IPS |
|
Image Super-Resolution (F16)
|
100% |
1147
41.0 IPS |
|
Image Super-Resolution (I8)
|
100% |
968
34.6 IPS |
|
Text Classification (F32)
|
100% |
60
86.4 IPS |
|
Text Classification (F16)
|
100% |
104
149.8 IPS |
|
Text Classification (I8)
|
96% |
105
151.5 IPS |
|
Machine Translation (F32)
|
100% |
210
3.86 IPS |
|
Machine Translation (F16)
|
100% |
170
3.12 IPS |
|
Machine Translation (I8)
|
99% |
201
3.71 IPS |