Question about training USRNet

[1144181135]

Hello, I have some questions about training USRNet. When I read the training code, I can not find where the optimization of equation 5 and 6. In the lines 149-152 of https://github.com/cszn/KAIR/blob/master/models/model_plain.py, it seems that only l1 loss and conventional backward are used in the code. Can you point out the part in which the optimization of equation 5 and 6? Thank you!

[cszn]

https://github.com/cszn/KAIR/blob/72e93351bca41d1b1f6a4c3e1957f5bffccc7101/models/network_usrnet_v1.py#L228

[zengyi319]

Thank you Kai Zhang. I have another question about training dpsr https://arxiv.org/pdf/2008.13751.pdf. About the optimization of eq. 6a and 6b, in the Algorithm 1, it seems that K iterations are in each training sample. However, I can not find the code for K iterations in neither models/network_dpsr.py or models/model_plain.py, Can you point out the part in which the optimization of eq. 6a and 6b ( K iterations in Algorithm 1 )? Thank you !

[cszn]

https://github.com/cszn/DPSR/blob/a5aa2728504b21c1585ef5983bf67db273b10736/demo_test_dpsr.py#L192