Upload Date | May 22 2024 02:27 PM |
Views | 1 |
System Information | |
---|---|
Operating System | iOS 17.5.1 |
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% |
3382
632.9 IPS |
|
Image Classification (F16)
|
100% |
3397
635.7 IPS |
|
Image Classification (I8)
|
99% |
3157
590.8 IPS |
|
Image Segmentation (F32)
|
100% |
1448
24.2 IPS |
|
Image Segmentation (F16)
|
100% |
1531
25.6 IPS |
|
Image Segmentation (I8)
|
100% |
1510
25.2 IPS |
|
Pose Estimation (F32)
|
100% |
22781
27.6 IPS |
|
Pose Estimation (F16)
|
100% |
25169
30.5 IPS |
|
Pose Estimation (I8)
|
100% |
24602
29.8 IPS |
|
Object Detection (F32)
|
100% |
2829
211.2 IPS |
|
Object Detection (F16)
|
100% |
2941
219.5 IPS |
|
Object Detection (I8)
|
97% |
2678
199.9 IPS |
|
Face Detection (F32)
|
100% |
9417
112.0 IPS |
|
Face Detection (F16)
|
98% |
10740
127.7 IPS |
|
Face Detection (I8)
|
97% |
10298
122.4 IPS |
|
Depth Estimation (F32)
|
100% |
16214
125.7 IPS |
|
Depth Estimation (F16)
|
100% |
17965
139.3 IPS |
|
Depth Estimation (I8)
|
37% |
16250
126.0 IPS |
|
Style Transfer (F32)
|
100% |
39403
51.8 IPS |
|
Style Transfer (F16)
|
100% |
43080
56.7 IPS |
|
Style Transfer (I8)
|
100% |
42777
56.3 IPS |
|
Image Super-Resolution (F32)
|
100% |
8402
300.1 IPS |
|
Image Super-Resolution (F16)
|
100% |
8364
298.7 IPS |
|
Image Super-Resolution (I8)
|
100% |
9691
346.1 IPS |
|
Text Classification (F32)
|
100% |
1102
1.58 KIPS |
|
Text Classification (F16)
|
100% |
745
1.07 KIPS |
|
Text Classification (I8)
|
96% |
746
1.07 KIPS |
|
Machine Translation (F32)
|
100% |
809
14.9 IPS |
|
Machine Translation (F16)
|
100% |
812
14.9 IPS |
|
Machine Translation (I8)
|
99% |
747
13.7 IPS |