Jianxu Chen
Jianxu Chen
I really appreciate the nice implementation of RNN. I came across a question when I am trying to understand the training procedure. In line the function feval(x), the variable "grad_params"...
https://github.com/1Konny/Beta-VAE/blob/master/main.py#L26 traverse( ) is not a member of net
### Is there an existing issue for this? - [X] I have searched the existing issues ### Bug summary I am testing to use Pytorch-lightning to handle model training (easy...
### Is there an existing issue for this? - [X] I have searched the existing issues ### Problem summary manually add_image (created by numpy array, not file path) causes dataloader...
Fixes #570. **Description** adapt CropOrPad function into a new RandomCropOrPad function, so that the source subject can be randomly cropped or padded into the target shape. **Checklist** - [x] I...
Just have a weird question. I find this super cool and very productive. But, what if some senior co-authors still like to use the old fashioned "track changes" in MS...
When creating the hessian matrix, it should be hessian_full=[[()] * ndim for x in range(ndim)] instead of hessian_full = [[None] * ndim] * ndim
**Describe the bug** when installing the package via pypi, there is a meta data mismatch: ``` Requested pyradiomics from https://files.pythonhosted.org/packages/03/c1/20fc2c50ab1e3304da36d866042a1905a2b05a1431ece35448ab6b4578f2/pyradiomics-3.1.0.tar.gz has inconsistent version: expected '3.1.0', but metadata has '3.0.1a1' ```...
It looks like there is a requirement on the minimum number of z slices. "ValueError: Input array must be at least length 32 in first dimension" When batch-processing on a...
add documentation and example for new Python API