Jianxu Chen

Results 15 comments of Jianxu Chen

https://github.com/AllenInstitute/aics-segmentation/blob/master/aicssegmentation/bin/batch_processing.py This is the batch processing function provided in `aics-segmentation`. It is nothing more than looping through the files one by one. Adding dask support seems to be an important...

First of all, by default, we are using [1.0, 1.0, 1.0] spacing in our segmentation algorithms even though our images are not isotropic. In practice, in our images (ZYX =...

Technically, the issue you pointed out is true, where users can change the spacing if they need. I will fix it in the next release.

> Do we know why there is a requirement for a minimum number of z stacks to be 32? In the nature methods paper, I do not see why 32...

> @jxchen01 do you know where the pooling layers are defined? Actually, it is convolution with stride = 2. See: https://github.com/AllenCellModeling/pytorch_fnet/blob/master/fnet/nn_modules/fnet_nn_3d_params.py#L51 The number of such layers is defined by `depth`:...