First of all thank you very much for this excellent work that you have open sourced, I am reading through the code and have come across something I don't understand, so I want to ask you a few questions.
In 2D S3_DSConv.py lines 289 to 298 'base' appears:
I understand that 'base' is used to correspond to the different images in single batch, but by adding base and then subtracting it immediately after in the code, I think this causes the subsequent value_a0 value_a1 value_c0 value_c1 to correspond only to the 0th image in a batch, which I feel affects the results of the bilinear interpolation.
Logic in 2D S3_DSConv.py lines 270-272 of code':
In these two lines of code, the input features are first flatten and then reshape to the original dimension, I don't understand the reason for this.
In 2D S3_DSConv.py lines 225-227 the code calculates the offset:
The loop doesn't seem to process to the outermost convolution kernel offset.
首先十分感谢您所开源的这份优秀工作，我在阅读代码时遇到了一些不懂的地方，因此想请教您几个问题。
在2D S3_DSConv.py 289行到298行出现的'base'： 我理解的base用于对应batch中的不同图像，但是在代码中加入base后紧接着又减去了base，我认为这会导致后续的value_a0 value_a1 value_c0 value_c1仅对应batch中第0个图像，感觉会影响双线性插值的结果。
在2D S3_DSConv.py 270-272行代码的逻辑'： 在这两行代码中，首先将输入特征flatten，接着又reshape到原维度，我不理解这样做的原因。
在2D S3_DSConv.py 225-227行代码计算offset时： 循环似乎没有处理到最外层的卷积核offset。
First of all thank you very much for this excellent work that you have open sourced, I am reading through the code and have come across something I don't understand, so I want to ask you a few questions.
In 2D S3_DSConv.py lines 289 to 298 'base' appears: I understand that 'base' is used to correspond to the different images in single batch, but by adding base and then subtracting it immediately after in the code, I think this causes the subsequent value_a0 value_a1 value_c0 value_c1 to correspond only to the 0th image in a batch, which I feel affects the results of the bilinear interpolation.
Logic in 2D S3_DSConv.py lines 270-272 of code': In these two lines of code, the input features are first flatten and then reshape to the original dimension, I don't understand the reason for this.
In 2D S3_DSConv.py lines 225-227 the code calculates the offset: The loop doesn't seem to process to the outermost convolution kernel offset.
期待您的回复。