Upload Date | May 16 2024 02:25 AM |
Views | 3 |
System Information | |
---|---|
Operating System | iOS 17.5 |
Model | iPad14,8 |
Model ID | iPad14,8 |
Motherboard | J507AP |
CPU Information | |
---|---|
Name | ARM |
Topology | 1 Processor, 8 Cores |
Identifier | ARM |
Base Frequency | 3.47 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 | 7.47 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
2820
527.8 IPS |
|
Image Classification (F16)
|
100% |
2880
539.0 IPS |
|
Image Classification (I8)
|
99% |
2656
497.1 IPS |
|
Image Segmentation (F32)
|
100% |
1387
23.2 IPS |
|
Image Segmentation (F16)
|
100% |
1438
24.0 IPS |
|
Image Segmentation (I8)
|
100% |
1441
24.1 IPS |
|
Pose Estimation (F32)
|
100% |
20724
25.1 IPS |
|
Pose Estimation (F16)
|
100% |
22635
27.4 IPS |
|
Pose Estimation (I8)
|
100% |
22145
26.8 IPS |
|
Object Detection (F32)
|
100% |
2107
157.3 IPS |
|
Object Detection (F16)
|
100% |
2647
197.6 IPS |
|
Object Detection (I8)
|
97% |
1243
92.8 IPS |
|
Face Detection (F32)
|
100% |
8883
105.6 IPS |
|
Face Detection (F16)
|
98% |
9931
118.1 IPS |
|
Face Detection (I8)
|
97% |
9525
113.3 IPS |
|
Depth Estimation (F32)
|
100% |
14841
115.1 IPS |
|
Depth Estimation (F16)
|
100% |
16239
125.9 IPS |
|
Depth Estimation (I8)
|
37% |
14908
115.6 IPS |
|
Style Transfer (F32)
|
100% |
36563
48.1 IPS |
|
Style Transfer (F16)
|
100% |
43132
56.7 IPS |
|
Style Transfer (I8)
|
100% |
42444
55.8 IPS |
|
Image Super-Resolution (F32)
|
100% |
6518
232.8 IPS |
|
Image Super-Resolution (F16)
|
100% |
5604
200.1 IPS |
|
Image Super-Resolution (I8)
|
100% |
6726
240.2 IPS |
|
Text Classification (F32)
|
100% |
1111
1.60 KIPS |
|
Text Classification (F16)
|
100% |
740
1.06 KIPS |
|
Text Classification (I8)
|
96% |
740
1.06 KIPS |
|
Machine Translation (F32)
|
100% |
647
11.9 IPS |
|
Machine Translation (F16)
|
100% |
680
12.5 IPS |
|
Machine Translation (I8)
|
99% |
641
11.8 IPS |