Help with multilabel image list

Part 1 (2019)
1

Hello,

I have dataset that looks like this

data/
train/
valid/
test/
labels.csv

And inside the labels.csv

	image_name	tags
0	fer0000000.png	neutral anger
1	fer0000001.png	neutral
2	fer0000002.png	neutral sadness
3	fer0000003.png	neutral sadness

Now I tried to copy the planet lesson, but I dont know how to use my folders to split the validation set.

path.ls()

[PosixPath('fer/train'),
PosixPath('fer/fer+formatted.csv'),
PosixPath('fer/valid'),
PosixPath('fer/test')]

src = (ImageList.from_csv(path,'fer+formatted.csv')
    .split_by_folder()
    .label_from_df(label_delim=' ')
    .databunch()
)

/opt/conda/lib/python3.6/site-packages/fastai/data_block.py:442: UserWarning: Your training set is empty. If this is by design, pass `ignore_empty=True` to remove this warning.
  warn("Your training set is empty. If this is by design, pass `ignore_empty=True` to remove this warning.")
/opt/conda/lib/python3.6/site-packages/fastai/data_block.py:445: UserWarning: Your validation set is empty. If this is by design, use `split_none()`
             or pass `ignore_empty=True` when labelling to remove this warning.
  or pass `ignore_empty=True` when labelling to remove this warning.""")

I spend so many time on this, please help me :smiley: