User | karen_he |
Upload Date | June 11 2024 07:10 PM |
Views | 3 |
System Information | |
---|---|
Operating System | iOS 18.0 |
Model | iPad14,6 |
Model ID | iPad14,6 |
Motherboard | J621AP |
CPU Information | |
---|---|
Name | ARM |
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 | 15.35 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
3314
620.1 IPS |
|
Image Classification (F16)
|
100% |
3577
669.4 IPS |
|
Image Classification (I8)
|
99% |
3160
591.3 IPS |
|
Image Segmentation (F32)
|
100% |
1433
23.9 IPS |
|
Image Segmentation (F16)
|
100% |
1514
25.3 IPS |
|
Image Segmentation (I8)
|
100% |
1505
25.1 IPS |
|
Pose Estimation (F32)
|
100% |
23473
28.4 IPS |
|
Pose Estimation (F16)
|
100% |
25349
30.7 IPS |
|
Pose Estimation (I8)
|
100% |
24559
29.7 IPS |
|
Object Detection (F32)
|
100% |
2853
213.0 IPS |
|
Object Detection (F16)
|
100% |
2991
223.3 IPS |
|
Object Detection (I8)
|
97% |
2642
197.2 IPS |
|
Face Detection (F32)
|
100% |
8947
106.4 IPS |
|
Face Detection (F16)
|
98% |
11272
134.0 IPS |
|
Face Detection (I8)
|
97% |
10891
129.5 IPS |
|
Depth Estimation (F32)
|
100% |
16241
125.9 IPS |
|
Depth Estimation (F16)
|
100% |
17631
136.7 IPS |
|
Depth Estimation (I8)
|
99% |
16072
124.6 IPS |
|
Style Transfer (F32)
|
100% |
37946
49.9 IPS |
|
Style Transfer (F16)
|
100% |
46603
61.3 IPS |
|
Style Transfer (I8)
|
100% |
46377
61.0 IPS |
|
Image Super-Resolution (F32)
|
100% |
9776
349.1 IPS |
|
Image Super-Resolution (F16)
|
100% |
10226
365.2 IPS |
|
Image Super-Resolution (I8)
|
100% |
9588
342.4 IPS |
|
Text Classification (F32)
|
100% |
2082
2.99 KIPS |
|
Text Classification (F16)
|
100% |
3410
4.90 KIPS |
|
Text Classification (I8)
|
96% |
3393
4.88 KIPS |
|
Machine Translation (F32)
|
100% |
882
16.2 IPS |
|
Machine Translation (F16)
|
100% |
865
15.9 IPS |
|
Machine Translation (I8)
|
99% |
841
15.5 IPS |