High Power Laser and Particle Beams, Volume. 35, Issue 11, 114005(2023)
Measurement of transverse phase space based on machine learning
Figures & Tables(14)
Fig. 4. Function diagram of focusing parameterk and rotation angle
Fig. 6. Rotation angles corresponding to different sampling methods
Fig. 9. An example of the interpolation network results in the form of sinogram
Fig. 10. An example of the interpolation network results in the form of tomography
Table 1. Residual U-Net network parameter settings
View tableView in ArticleTable 1. Residual U-Net network parameter settings
name parameters output Conv_block_1 1 $ \times $ 1 conv, 64200 $ \times $ 57, 643 $ \times $ 3 conv, 64Conv_block_2 2 $ \times $ 3 conv, s=2, p=0, 64100 $ \times $ 28, 64[3 $ \times $ 3 conv, 64]$ \times $ 2Conv_block_3 2 $ \times $ 2 conv, s=2, p=0, 6450 $ \times $ 14, 64[3 $ \times $ 3 conv, 64]$ \times $ 2Conv_block_4 2 $ \times $ 2 conv, s=2, p=0, 6425 $ \times $ 7, 64[3 $ \times $ 3 conv, 64]$ \times $ 2ConvT_block_1 $2 \times 2$ convT, s=2, p=0, 6450 $ \times $ 14, 64ConvT_block_2 Conv_block_3, concatenation 100 $ \times $ 28, 64[ $3 \times 3$ conv,64]$ \times $ 2$2 \times 2$ convT, s=2, p=0, 64ConvT_block_3 Conv_block_2, concatenation 200 $ \times $ 57, 64[ $3 \times 3$ conv, 64]$ \times $ 2$2 \times 3$ convT, s=2, p=0, 64Conv_block_5 Conv_block_1, concatenation 200 $ \times $ 57, 1$3 \times 3$ conv,16$3 \times 3$ conv, 1shortcut connection
Table 2. RED-CNN network parameter settings
View tableView in ArticleTable 2. RED-CNN network parameter settings
name parameters output Conv_1 [5, Conv, 16] $ \times $ 2192 $ \times $ 192, 16Conv_2 [5, Conv, 16] $ \times $ 2184 $ \times $ 184, 16Conv_3 [5, Conv, 16] $ \times $ 2176 $ \times $ 176, 16ConvT_1 [5, ConvT, 16] $ \times $ 2184 $ \times $ 184, 16ConvT_2 Conv_2, addition 192 $ \times $ 192, 16[5, convT, 16] $ \times $ 2ConvT_3 Conv_1, addition 200 $ \times $ 200, 1[5, convT1, 1] $ \times $ 2shortcut connection
Tools
Get Citation
Copy Citation Text
Yutao Han, Renkai Li, Weishi Wan. Measurement of transverse phase space based on machine learning[J]. High Power Laser and Particle Beams, 2023, 35(11): 114005
Paper Information
Category:
Received: Apr. 4, 2023
Accepted: Oct. 19, 2023
Published Online: Dec. 26, 2023
The Author Email:
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20