Upload Date | May 21 2024 02:45 AM |
Views | 1 |
System Information | |
---|---|
Operating System | iOS 16.5 |
Model | iPad Pro (12.9-inch, 6th generation) |
Model ID | iPad14,5 |
Motherboard | J620AP |
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 | 7.33 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
3484
652.0 IPS |
|
Image Classification (F16)
|
100% |
3457
646.8 IPS |
|
Image Classification (I8)
|
99% |
3473
649.9 IPS |
|
Image Segmentation (F32)
|
100% |
879
14.7 IPS |
|
Image Segmentation (F16)
|
100% |
866
14.5 IPS |
|
Image Segmentation (I8)
|
100% |
852
14.2 IPS |
|
Pose Estimation (F32)
|
100% |
23781
28.8 IPS |
|
Pose Estimation (F16)
|
100% |
25270
30.6 IPS |
|
Pose Estimation (I8)
|
100% |
25070
30.4 IPS |
|
Object Detection (F32)
|
100% |
3056
228.2 IPS |
|
Object Detection (F16)
|
100% |
3168
236.5 IPS |
|
Object Detection (I8)
|
97% |
3026
225.9 IPS |
|
Face Detection (F32)
|
100% |
9826
116.8 IPS |
|
Face Detection (F16)
|
97% |
11200
133.2 IPS |
|
Face Detection (I8)
|
96% |
11208
133.3 IPS |
|
Depth Estimation (F32)
|
100% |
16302
126.4 IPS |
|
Depth Estimation (F16)
|
100% |
17346
134.5 IPS |
|
Depth Estimation (I8)
|
99% |
17143
132.9 IPS |
|
Style Transfer (F32)
|
100% |
37609
49.5 IPS |
|
Style Transfer (F16)
|
100% |
46882
61.7 IPS |
|
Style Transfer (I8)
|
100% |
46634
61.3 IPS |
|
Image Super-Resolution (F32)
|
100% |
9334
333.4 IPS |
|
Image Super-Resolution (F16)
|
100% |
9962
355.8 IPS |
|
Image Super-Resolution (I8)
|
100% |
9986
356.6 IPS |
|
Text Classification (F32)
|
100% |
903
1.30 KIPS |
|
Text Classification (F16)
|
100% |
898
1.29 KIPS |
|
Text Classification (I8)
|
96% |
857
1.23 KIPS |
|
Machine Translation (F32)
|
100% |
1349
24.8 IPS |
|
Machine Translation (F16)
|
100% |
1379
25.4 IPS |
|
Machine Translation (I8)
|
99% |
1339
24.6 IPS |