Upload Date | May 11 2024 11:49 AM |
Views | 7 |
System Information | |
---|---|
Operating System | iOS 17.5 |
Model | iPad16,4 |
Model ID | iPad16,4 |
Motherboard | J718AP |
CPU Information | |
---|---|
Name | ARM |
Topology | 1 Processor, 10 Cores |
Identifier | ARM |
Base Frequency | 4.40 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 6 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 | 15.13 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
4190
784.1 IPS |
|
Image Classification (F16)
|
100% |
4416
826.3 IPS |
|
Image Classification (I8)
|
99% |
4062
760.1 IPS |
|
Image Segmentation (F32)
|
100% |
2031
33.9 IPS |
|
Image Segmentation (F16)
|
100% |
2283
38.1 IPS |
|
Image Segmentation (I8)
|
100% |
2203
36.8 IPS |
|
Pose Estimation (F32)
|
100% |
26875
32.5 IPS |
|
Pose Estimation (F16)
|
100% |
28930
35.0 IPS |
|
Pose Estimation (I8)
|
100% |
28170
34.1 IPS |
|
Object Detection (F32)
|
100% |
3368
251.4 IPS |
|
Object Detection (F16)
|
100% |
3914
292.2 IPS |
|
Object Detection (I8)
|
97% |
3395
253.5 IPS |
|
Face Detection (F32)
|
100% |
11372
135.2 IPS |
|
Face Detection (F16)
|
98% |
14032
166.8 IPS |
|
Face Detection (I8)
|
97% |
13590
161.6 IPS |
|
Depth Estimation (F32)
|
100% |
19642
152.3 IPS |
|
Depth Estimation (F16)
|
100% |
22063
171.1 IPS |
|
Depth Estimation (I8)
|
37% |
20194
156.6 IPS |
|
Style Transfer (F32)
|
100% |
56581
74.4 IPS |
|
Style Transfer (F16)
|
100% |
65206
85.8 IPS |
|
Style Transfer (I8)
|
100% |
64699
85.1 IPS |
|
Image Super-Resolution (F32)
|
100% |
8947
319.5 IPS |
|
Image Super-Resolution (F16)
|
100% |
8451
301.8 IPS |
|
Image Super-Resolution (I8)
|
100% |
8602
307.2 IPS |
|
Text Classification (F32)
|
100% |
1251
1.80 KIPS |
|
Text Classification (F16)
|
100% |
1453
2.09 KIPS |
|
Text Classification (I8)
|
96% |
1112
1.60 KIPS |
|
Machine Translation (F32)
|
100% |
1040
19.1 IPS |
|
Machine Translation (F16)
|
100% |
1051
19.3 IPS |
|
Machine Translation (I8)
|
99% |
892
16.4 IPS |