User | j0hnd03 |
Upload Date | January 19 2024 07:13 PM |
Views | 2 |
System Information | |
---|---|
Operating System | iOS 17.2 |
Model | iPad Air (5th generation) |
Model ID | iPad13,16 |
Motherboard | J407AP |
CPU Information | |
---|---|
Name | Apple M1 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM |
Base Frequency | 3.19 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% |
1254
234.7 IPS |
|
Image Classification (F16)
|
100% |
1081
202.3 IPS |
|
Image Classification (I8)
|
99% |
1221
228.4 IPS |
|
Image Segmentation (F32)
|
100% |
826
13.8 IPS |
|
Image Segmentation (F16)
|
100% |
881
14.7 IPS |
|
Image Segmentation (I8)
|
100% |
898
15.0 IPS |
|
Pose Estimation (F32)
|
100% |
16487
20.0 IPS |
|
Pose Estimation (F16)
|
100% |
18052
21.9 IPS |
|
Pose Estimation (I8)
|
100% |
17633
21.4 IPS |
|
Object Detection (F32)
|
100% |
1473
110.0 IPS |
|
Object Detection (F16)
|
100% |
1416
105.7 IPS |
|
Object Detection (I8)
|
97% |
1527
114.0 IPS |
|
Face Detection (F32)
|
100% |
6056
72.0 IPS |
|
Face Detection (F16)
|
97% |
7233
86.0 IPS |
|
Face Detection (I8)
|
96% |
7152
85.0 IPS |
|
Depth Estimation (F32)
|
100% |
12168
94.4 IPS |
|
Depth Estimation (F16)
|
100% |
13719
106.4 IPS |
|
Depth Estimation (I8)
|
37% |
12402
96.2 IPS |
|
Style Transfer (F32)
|
100% |
26743
35.2 IPS |
|
Style Transfer (F16)
|
100% |
30217
39.7 IPS |
|
Style Transfer (I8)
|
100% |
33933
44.6 IPS |
|
Image Super-Resolution (F32)
|
100% |
4975
177.7 IPS |
|
Image Super-Resolution (F16)
|
100% |
5518
197.1 IPS |
|
Image Super-Resolution (I8)
|
100% |
5366
191.6 IPS |
|
Text Classification (F32)
|
100% |
1148
1.65 KIPS |
|
Text Classification (F16)
|
100% |
758
1.09 KIPS |
|
Text Classification (I8)
|
96% |
758
1.09 KIPS |
|
Machine Translation (F32)
|
100% |
558
10.3 IPS |
|
Machine Translation (F16)
|
100% |
566
10.4 IPS |
|
Machine Translation (I8)
|
99% |
525
9.67 IPS |