Upload Date | May 09 2024 11:33 AM |
Views | 1 |
System Information | |
---|---|
Operating System | iOS 17.4.1 |
Model | iPad Pro (11-inch, 4th generation) |
Model ID | iPad14,3 |
Motherboard | J617AP |
CPU Information | |
---|---|
Name | Apple M2 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM |
Base Frequency | 3.49 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
L1 Instruction Cache | 128 KB x 1 |
L1 Data Cache | 64.0 KB x 1 |
L2 Cache | 4.00 MB x 1 |
Memory Information | |
---|---|
Size | 7.33 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
3365
629.7 IPS |
|
Image Classification (F16)
|
100% |
3352
627.2 IPS |
|
Image Classification (I8)
|
99% |
3030
567.0 IPS |
|
Image Segmentation (F32)
|
100% |
1439
24.0 IPS |
|
Image Segmentation (F16)
|
100% |
1530
25.6 IPS |
|
Image Segmentation (I8)
|
100% |
1511
25.2 IPS |
|
Pose Estimation (F32)
|
100% |
23579
28.6 IPS |
|
Pose Estimation (F16)
|
100% |
25004
30.3 IPS |
|
Pose Estimation (I8)
|
100% |
24377
29.5 IPS |
|
Object Detection (F32)
|
100% |
2828
211.2 IPS |
|
Object Detection (F16)
|
100% |
2843
212.3 IPS |
|
Object Detection (I8)
|
97% |
2586
193.1 IPS |
|
Face Detection (F32)
|
100% |
9310
110.7 IPS |
|
Face Detection (F16)
|
98% |
10545
125.4 IPS |
|
Face Detection (I8)
|
97% |
10024
119.2 IPS |
|
Depth Estimation (F32)
|
100% |
16326
126.6 IPS |
|
Depth Estimation (F16)
|
100% |
17572
136.3 IPS |
|
Depth Estimation (I8)
|
37% |
15917
123.4 IPS |
|
Style Transfer (F32)
|
100% |
40365
53.1 IPS |
|
Style Transfer (F16)
|
100% |
46909
61.7 IPS |
|
Style Transfer (I8)
|
100% |
43233
56.9 IPS |
|
Image Super-Resolution (F32)
|
100% |
9460
337.9 IPS |
|
Image Super-Resolution (F16)
|
100% |
8407
300.2 IPS |
|
Image Super-Resolution (I8)
|
100% |
8141
290.8 IPS |
|
Text Classification (F32)
|
100% |
1104
1.59 KIPS |
|
Text Classification (F16)
|
100% |
742
1.07 KIPS |
|
Text Classification (I8)
|
96% |
743
1.07 KIPS |
|
Machine Translation (F32)
|
100% |
813
15.0 IPS |
|
Machine Translation (F16)
|
100% |
820
15.1 IPS |
|
Machine Translation (I8)
|
99% |
788
14.5 IPS |