Upload Date | July 27 2024 01:23 AM |
Views | 1 |
System Information | |
---|---|
Operating System | iOS 17.5.1 |
Model | iPad Pro (11-inch) |
Model ID | iPad8,1 |
Motherboard | J317AP |
CPU Information | |
---|---|
Name | Apple A12X Bionic |
Topology | 1 Processor, 8 Cores |
Identifier | ARM |
Base Frequency | 2.49 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
L1 Instruction Cache | 48.0 KB x 1 |
L1 Data Cache | 32.0 KB x 1 |
L2 Cache | 2.00 MB x 1 |
Memory Information | |
---|---|
Size | 3.69 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
782
146.4 IPS |
|
Image Classification (F16)
|
100% |
2143
401.1 IPS |
|
Image Classification (I8)
|
99% |
2147
401.8 IPS |
|
Image Segmentation (F32)
|
100% |
241
4.02 IPS |
|
Image Segmentation (F16)
|
100% |
258
4.30 IPS |
|
Image Segmentation (I8)
|
100% |
257
4.30 IPS |
|
Pose Estimation (F32)
|
100% |
2665
3.23 IPS |
|
Pose Estimation (F16)
|
100% |
24373
29.5 IPS |
|
Pose Estimation (I8)
|
100% |
24572
29.8 IPS |
|
Object Detection (F32)
|
100% |
821
61.3 IPS |
|
Object Detection (F16)
|
100% |
1074
80.2 IPS |
|
Object Detection (I8)
|
97% |
840
62.7 IPS |
|
Face Detection (F32)
|
100% |
3153
37.5 IPS |
|
Face Detection (F16)
|
98% |
3903
46.4 IPS |
|
Face Detection (I8)
|
97% |
3838
45.6 IPS |
|
Depth Estimation (F32)
|
100% |
2989
23.2 IPS |
|
Depth Estimation (F16)
|
100% |
20620
159.9 IPS |
|
Depth Estimation (I8)
|
99% |
19542
151.5 IPS |
|
Style Transfer (F32)
|
100% |
7676
10.1 IPS |
|
Style Transfer (F16)
|
100% |
9237
12.2 IPS |
|
Style Transfer (I8)
|
100% |
9207
12.1 IPS |
|
Image Super-Resolution (F32)
|
100% |
1562
55.8 IPS |
|
Image Super-Resolution (F16)
|
100% |
3742
133.6 IPS |
|
Image Super-Resolution (I8)
|
100% |
3770
134.7 IPS |
|
Text Classification (F32)
|
100% |
199
285.5 IPS |
|
Text Classification (F16)
|
100% |
237
340.0 IPS |
|
Text Classification (I8)
|
96% |
235
337.7 IPS |
|
Machine Translation (F32)
|
100% |
359
6.61 IPS |
|
Machine Translation (F16)
|
100% |
351
6.45 IPS |
|
Machine Translation (I8)
|
99% |
359
6.60 IPS |