Upload Date | May 08 2024 03:07 AM |
Views | 1 |
System Information | |
---|---|
Operating System | iOS 17.4.1 |
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 | 7.33 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
3308
619.0 IPS |
|
Image Classification (F16)
|
100% |
3391
634.6 IPS |
|
Image Classification (I8)
|
99% |
3023
565.7 IPS |
|
Image Segmentation (F32)
|
100% |
1449
24.2 IPS |
|
Image Segmentation (F16)
|
100% |
1557
26.0 IPS |
|
Image Segmentation (I8)
|
100% |
1528
25.5 IPS |
|
Pose Estimation (F32)
|
100% |
22576
27.3 IPS |
|
Pose Estimation (F16)
|
100% |
24972
30.2 IPS |
|
Pose Estimation (I8)
|
100% |
24471
29.6 IPS |
|
Object Detection (F32)
|
100% |
2680
200.0 IPS |
|
Object Detection (F16)
|
100% |
2864
213.8 IPS |
|
Object Detection (I8)
|
97% |
2608
194.7 IPS |
|
Face Detection (F32)
|
100% |
9300
110.6 IPS |
|
Face Detection (F16)
|
98% |
10551
125.5 IPS |
|
Face Detection (I8)
|
97% |
10082
119.9 IPS |
|
Depth Estimation (F32)
|
100% |
15982
123.9 IPS |
|
Depth Estimation (F16)
|
100% |
17394
134.9 IPS |
|
Depth Estimation (I8)
|
37% |
16007
124.1 IPS |
|
Style Transfer (F32)
|
100% |
39379
51.8 IPS |
|
Style Transfer (F16)
|
100% |
42810
56.3 IPS |
|
Style Transfer (I8)
|
100% |
42775
56.3 IPS |
|
Image Super-Resolution (F32)
|
100% |
9446
337.4 IPS |
|
Image Super-Resolution (F16)
|
100% |
10128
361.7 IPS |
|
Image Super-Resolution (I8)
|
100% |
9629
343.9 IPS |
|
Text Classification (F32)
|
100% |
1127
1.62 KIPS |
|
Text Classification (F16)
|
100% |
742
1.07 KIPS |
|
Text Classification (I8)
|
96% |
758
1.09 KIPS |
|
Machine Translation (F32)
|
100% |
784
14.4 IPS |
|
Machine Translation (F16)
|
100% |
813
15.0 IPS |
|
Machine Translation (I8)
|
99% |
747
13.7 IPS |