Fernando Pérez-García
Fernando Pérez-García
My command: ```shell gem install charlock_holmes -- --with-icu-dir=/usr/local/opt/icu4c ``` Output: ``` Building native extensions with: '--with-icu-dir=/usr/local/opt/icu4c' This could take a while... ERROR: Error installing charlock_holmes: ERROR: Failed to build gem...
Hi, and thanks for sharing your work! I have run the notebook you shared on PyTorch Hub and added one cell: ```python import scipy.ndimage as ndi import matplotlib.pyplot as plt...
This float comparison can be problematic. https://github.com/NifTK/NiftyNet/blob/9b12da455dd8ed0a5e8e5060c4e939aa62d68c5a/niftynet/utilities/histogram_standardisation.py#L189 I was getting `-inf` in the output of the function because `1.6e-41 == 0` was returning `False`. I think an epsilon should be...
Default values for the bias field layer coefficients might be too large: https://github.com/NifTK/NiftyNet/blob/a383ba342e3e38a7ad7eed7538bfb34960f80c8d/niftynet/layer/rand_bias_field.py#L17-L18 I get sensible result with the values in this config: https://github.com/NifTK/NiftyNet/blob/a383ba342e3e38a7ad7eed7538bfb34960f80c8d/config/default_segmentation_bf.ini#L55 @csudre
The [`smaller_final_batch_mode`](https://niftynet.readthedocs.io/en/dev/config_spec.html#smaller-final-batch-mode) parameter is ignored during training as the dataset is "infinite" (samples yielded by a generator). Dropping a smaller batch won't happen. During inference, users will rarely want to...
It's not clear what [`interp_order`](https://niftynet.readthedocs.io/en/dev/config_spec.html#interp-order) and [`https://niftynet.readthedocs.io/en/dev/config_spec.html#output-interp-order`] are used for. Also, the config docs mention SimpleITK constants but sometimes `scipy.zoom` is used in the code.
It has always been hard for me to find the line containing information about the errors in NiftyNet output. Oftentimes I find the line that seems to give trouble, but...
I can work on this soon. The main one is [MICCAI](https://dblp.org/db/conf/miccai/index.html).
As in HI-ML: - https://github.com/microsoft/hi-ml/issues/463 [AB#6815](https://innereye.visualstudio.com/60ce1777-00d6-4015-82bc-488a0c00202f/_workitems/edit/6815)