Upload Date | May 08 2024 09:53 AM |
Views | 1 |
System Information | |
---|---|
Operating System | iOS 17.4.1 |
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 | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
1283
240.2 IPS |
|
Image Classification (F16)
|
100% |
1667
311.9 IPS |
|
Image Classification (I8)
|
99% |
1675
313.4 IPS |
|
Image Segmentation (F32)
|
100% |
600
10.0 IPS |
|
Image Segmentation (F16)
|
100% |
594
9.92 IPS |
|
Image Segmentation (I8)
|
100% |
594
9.92 IPS |
|
Pose Estimation (F32)
|
100% |
5635
6.82 IPS |
|
Pose Estimation (F16)
|
100% |
12942
15.7 IPS |
|
Pose Estimation (I8)
|
100% |
12941
15.7 IPS |
|
Object Detection (F32)
|
100% |
1309
97.8 IPS |
|
Object Detection (F16)
|
100% |
1735
129.5 IPS |
|
Object Detection (I8)
|
97% |
1306
97.5 IPS |
|
Face Detection (F32)
|
100% |
2374
28.2 IPS |
|
Face Detection (F16)
|
97% |
4004
47.6 IPS |
|
Face Detection (I8)
|
97% |
4012
47.7 IPS |
|
Depth Estimation (F32)
|
100% |
5199
40.3 IPS |
|
Depth Estimation (F16)
|
100% |
8152
63.2 IPS |
|
Depth Estimation (I8)
|
99% |
8160
63.3 IPS |
|
Style Transfer (F32)
|
100% |
15673
20.6 IPS |
|
Style Transfer (F16)
|
100% |
24327
32.0 IPS |
|
Style Transfer (I8)
|
100% |
24385
32.1 IPS |
|
Image Super-Resolution (F32)
|
100% |
3463
123.7 IPS |
|
Image Super-Resolution (F16)
|
100% |
4564
163.0 IPS |
|
Image Super-Resolution (I8)
|
100% |
4507
161.0 IPS |
|
Text Classification (F32)
|
100% |
2102
3.02 KIPS |
|
Text Classification (F16)
|
100% |
3432
4.93 KIPS |
|
Text Classification (I8)
|
96% |
3351
4.82 KIPS |
|
Machine Translation (F32)
|
100% |
733
13.5 IPS |
|
Machine Translation (F16)
|
100% |
869
16.0 IPS |
|
Machine Translation (I8)
|
99% |
733
13.5 IPS |