Upload Date | August 15 2024 01:10 PM |
Views | 2 |
System Information | |
---|---|
Operating System | iOS 17.6.1 |
Model | iPad Pro (12.9-inch 5th generation) |
Model ID | iPad13,8 |
Motherboard | J522AP |
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 | 7.31 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
1793
335.5 IPS |
|
Image Classification (F16)
|
100% |
1199
224.3 IPS |
|
Image Classification (I8)
|
99% |
1234
230.9 IPS |
|
Image Segmentation (F32)
|
100% |
847
14.1 IPS |
|
Image Segmentation (F16)
|
100% |
857
14.3 IPS |
|
Image Segmentation (I8)
|
100% |
853
14.2 IPS |
|
Pose Estimation (F32)
|
100% |
15966
19.3 IPS |
|
Pose Estimation (F16)
|
100% |
17610
21.3 IPS |
|
Pose Estimation (I8)
|
100% |
17519
21.2 IPS |
|
Object Detection (F32)
|
100% |
1471
109.8 IPS |
|
Object Detection (F16)
|
100% |
1465
109.4 IPS |
|
Object Detection (I8)
|
97% |
1527
114.0 IPS |
|
Face Detection (F32)
|
100% |
5856
69.6 IPS |
|
Face Detection (F16)
|
98% |
7208
85.7 IPS |
|
Face Detection (I8)
|
97% |
7157
85.1 IPS |
|
Depth Estimation (F32)
|
100% |
11976
92.9 IPS |
|
Depth Estimation (F16)
|
100% |
13535
105.0 IPS |
|
Depth Estimation (I8)
|
37% |
12617
97.8 IPS |
|
Style Transfer (F32)
|
100% |
27418
36.1 IPS |
|
Style Transfer (F16)
|
100% |
32736
43.1 IPS |
|
Style Transfer (I8)
|
100% |
33534
44.1 IPS |
|
Image Super-Resolution (F32)
|
100% |
4800
171.4 IPS |
|
Image Super-Resolution (F16)
|
100% |
5215
186.2 IPS |
|
Image Super-Resolution (I8)
|
100% |
5187
185.2 IPS |
|
Text Classification (F32)
|
100% |
1175
1.69 KIPS |
|
Text Classification (F16)
|
100% |
761
1.09 KIPS |
|
Text Classification (I8)
|
96% |
761
1.09 KIPS |
|
Machine Translation (F32)
|
100% |
533
9.81 IPS |
|
Machine Translation (F16)
|
100% |
537
9.89 IPS |
|
Machine Translation (I8)
|
99% |
540
9.93 IPS |