Pipeline for particle picking in cryo-electron microscopy images using convolutional neural networks trained from positive and unlabeled examples. Also featuring micrograph and tomogram denoising with DNNs.
Super small fix: the pandas df.iterrows() method reverts ints to floats, but in this case the results are used as list indices and must remain ints. This was causing exceptions/errors for me when using k-fold cross validation. See the Note at https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.iterrows.html
Replaced with df.itertuples() which preserves dtypes (as per suggestion in that same Note).
DarnellGranberry
commented
1 year ago
Super small fix: the pandas df.iterrows() method reverts ints to floats, but in this case the results are used as list indices and must remain ints. This was causing exceptions/errors for me when using k-fold cross validation. See the Note at https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.iterrows.html
Replaced with df.itertuples() which preserves dtypes (as per suggestion in that same Note).