Hafez Farazi

Hi, Do you think the following is correct? ``` def fft2(x): return np.fft.fft2(x) @adjoint(fft2) def dfft2(y, x): d[x] = np.fft.fft2(d[y]) def ifft2(x): return np.fft.ifft2(x) @adjoint(ifft2) def difft2(y, x): d[x] =...

You can implement it better!

3

https://github.com/zongyi-li/fourier_neural_operator/blob/90bbd4c9ffa84b91ec2daa86660148861989adec/fourier_3d.py#L53 What you can do is using FFTshift: ``` def roll_n(X, axis, n): f_idx = tuple(slice(None, None, None) if i != axis else slice(0, n, None) for i in range(X.dim()))...

see: https://github.com/zongyi-li/fourier_neural_operator/issues/10

how can i buy automatically using FuturePayment?

How can I reverse sents2elmo? I mean something like elmo2sents?

Point annotation is disabled after use of SAM annotation

1

After using positive and negative point prompt for SAM based auto annotate, even after disabling auto annotate, the regular point annotation is not possible. I don't think it is a...