User | suhaasnandeesh |
Upload Date | May 08 2024 10:32 AM |
Views | 2 |
System Information | |
---|---|
Operating System | iOS 17.4.1 |
Model | iPad mini (6th generation) |
Model ID | iPad14,1 |
Motherboard | J310AP |
CPU Information | |
---|---|
Name | Apple A15 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 2.92 GHz |
Cluster 1 | 2 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 | 3.78 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
529
99.0 IPS |
|
Image Classification (F16)
|
100% |
619
115.9 IPS |
|
Image Classification (I8)
|
99% |
521
97.6 IPS |
|
Image Segmentation (F32)
|
100% |
1009
16.8 IPS |
|
Image Segmentation (F16)
|
100% |
1059
17.7 IPS |
|
Image Segmentation (I8)
|
100% |
997
16.7 IPS |
|
Pose Estimation (F32)
|
100% |
10204
12.4 IPS |
|
Pose Estimation (F16)
|
100% |
11196
13.6 IPS |
|
Pose Estimation (I8)
|
100% |
11002
13.3 IPS |
|
Object Detection (F32)
|
100% |
716
53.5 IPS |
|
Object Detection (F16)
|
100% |
687
51.3 IPS |
|
Object Detection (I8)
|
97% |
777
58.0 IPS |
|
Face Detection (F32)
|
100% |
3207
38.1 IPS |
|
Face Detection (F16)
|
98% |
3616
43.0 IPS |
|
Face Detection (I8)
|
97% |
3435
40.8 IPS |
|
Depth Estimation (F32)
|
100% |
6903
53.5 IPS |
|
Depth Estimation (F16)
|
100% |
6850
53.1 IPS |
|
Depth Estimation (I8)
|
37% |
7540
58.5 IPS |
|
Style Transfer (F32)
|
100% |
18286
24.1 IPS |
|
Style Transfer (F16)
|
100% |
22516
29.6 IPS |
|
Style Transfer (I8)
|
100% |
22469
29.6 IPS |
|
Image Super-Resolution (F32)
|
100% |
2806
100.2 IPS |
|
Image Super-Resolution (F16)
|
100% |
2445
87.3 IPS |
|
Image Super-Resolution (I8)
|
100% |
2621
93.6 IPS |
|
Text Classification (F32)
|
100% |
357
512.9 IPS |
|
Text Classification (F16)
|
100% |
356
512.0 IPS |
|
Text Classification (I8)
|
96% |
225
323.3 IPS |
|
Machine Translation (F32)
|
100% |
449
8.27 IPS |
|
Machine Translation (F16)
|
100% |
464
8.54 IPS |
|
Machine Translation (I8)
|
99% |
410
7.54 IPS |