Upload Date | September 18 2024 09:02 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M1 |
System Information | |
---|---|
Operating System | iOS 18.0 |
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 |
Memory Information | |
---|---|
Size | 7.35 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1407
261.6 IPS |
|
Image Classification (HP)
|
100% |
6272
1.17 KIPS |
|
Image Classification (Q)
|
96% |
5876
1.10 KIPS |
|
Image Segmentation (SP)
|
100% |
1379
22.4 IPS |
|
Image Segmentation (HP)
|
100% |
6638
107.6 IPS |
|
Image Segmentation (Q)
|
99% |
6748
109.4 IPS |
|
Pose Estimation (SP)
|
100% |
6528
7.62 IPS |
|
Pose Estimation (HP)
|
100% |
68527
80.0 IPS |
|
Pose Estimation (Q)
|
95% |
66182
77.6 IPS |
|
Object Detection (SP)
|
100% |
1516
120.3 IPS |
|
Object Detection (HP)
|
99% |
7254
577.0 IPS |
|
Object Detection (Q)
|
91% |
6710
536.2 IPS |
|
Face Detection (SP)
|
100% |
3024
35.9 IPS |
|
Face Detection (HP)
|
100% |
16196
192.4 IPS |
|
Face Detection (Q)
|
100% |
15020
178.5 IPS |
|
Depth Estimation (SP)
|
100% |
5817
44.8 IPS |
|
Depth Estimation (HP)
|
99% |
47343
364.7 IPS |
|
Depth Estimation (Q)
|
85% |
48235
376.9 IPS |
|
Style Transfer (SP)
|
100% |
17156
22.1 IPS |
|
Style Transfer (HP)
|
100% |
120102
154.4 IPS |
|
Style Transfer (Q)
|
96% |
114966
148.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
3750
138.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
23180
855.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
23887
882.0 IPS |
|
Text Classification (SP)
|
100% |
2267
3.03 KIPS |
|
Text Classification (HP)
|
100% |
3934
5.25 KIPS |
|
Text Classification (Q)
|
93% |
3914
5.25 KIPS |
|
Machine Translation (SP)
|
100% |
2464
42.4 IPS |
|
Machine Translation (HP)
|
100% |
2330
40.1 IPS |
|
Machine Translation (Q)
|
98% |
2337
40.4 IPS |