Upload Date | October 18 2024 11:19 AM |
Views | 1 |
System Information | |
---|---|
Operating System | iOS 18.0.1 |
Model | iPad Pro (11-inch, 4th generation) |
Model ID | iPad14,3 |
Motherboard | J617AP |
CPU Information | |
---|---|
Name | Apple M2 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM |
Base Frequency | 3.49 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 | 7.37 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
1359
254.3 IPS |
|
Image Classification (F16)
|
100% |
2429
454.6 IPS |
|
Image Classification (I8)
|
99% |
2425
453.8 IPS |
|
Image Segmentation (F32)
|
100% |
871
14.5 IPS |
|
Image Segmentation (F16)
|
100% |
1084
18.1 IPS |
|
Image Segmentation (I8)
|
100% |
1082
18.1 IPS |
|
Pose Estimation (F32)
|
100% |
6616
8.01 IPS |
|
Pose Estimation (F16)
|
100% |
14232
17.2 IPS |
|
Pose Estimation (I8)
|
100% |
14189
17.2 IPS |
|
Object Detection (F32)
|
100% |
1445
107.8 IPS |
|
Object Detection (F16)
|
100% |
2411
180.0 IPS |
|
Object Detection (I8)
|
97% |
1443
107.8 IPS |
|
Face Detection (F32)
|
100% |
3065
36.4 IPS |
|
Face Detection (F16)
|
97% |
5936
70.6 IPS |
|
Face Detection (I8)
|
97% |
5973
71.0 IPS |
|
Depth Estimation (F32)
|
100% |
5615
43.5 IPS |
|
Depth Estimation (F16)
|
100% |
11510
89.3 IPS |
|
Depth Estimation (I8)
|
99% |
11546
89.5 IPS |
|
Style Transfer (F32)
|
100% |
18444
24.3 IPS |
|
Style Transfer (F16)
|
100% |
27855
36.6 IPS |
|
Style Transfer (I8)
|
100% |
28003
36.8 IPS |
|
Image Super-Resolution (F32)
|
100% |
4143
148.0 IPS |
|
Image Super-Resolution (F16)
|
100% |
5041
180.0 IPS |
|
Image Super-Resolution (I8)
|
100% |
4944
176.6 IPS |
|
Text Classification (F32)
|
100% |
2015
2.90 KIPS |
|
Text Classification (F16)
|
100% |
3276
4.71 KIPS |
|
Text Classification (I8)
|
96% |
3279
4.71 KIPS |
|
Machine Translation (F32)
|
100% |
1372
25.3 IPS |
|
Machine Translation (F16)
|
100% |
1626
29.9 IPS |
|
Machine Translation (I8)
|
99% |
1374
25.3 IPS |