ids in metadata.csv do not correspond to filenames ?

[amgsharma]

How does one link the metadata file to the image files? Also there seem to be less metadata than there are images?

[bganglia]

@amgsharma Use the filename column. You can join the path to the images directory with the filename from each row to obtain the path to each image.

[ieee8023]

You can use the dataloader here: https://github.com/mlmed/torchxrayvision just put the paths to the images and csv file.

[ankamdeepika]

You can use the dataloader here: https://github.com/mlmed/torchxrayvision just put the paths to the images and csv file.

can you please elaborate as in how to use the data loader?

[ieee8023]

can you please elaborate as in how to use the data loader?

You can use this as an example: https://github.com/ieee8023/covid-chestxray-dataset/blob/master/scripts/test_dataloader.py

[ankamdeepika]

can you please elaborate as in how to use the data loader?

You can use this as an example: https://github.com/ieee8023/covid-chestxray-dataset/blob/master/scripts/test_dataloader.py

its throwing this error ParserError: Error tokenizing data. C error: Expected 1 fields in line 71, saw 2

[ieee8023]

I just created an example here: https://colab.research.google.com/drive/1A-gIZ6Xp-eh2b4CGS6BHH7-OgZtyjeP2

[ankamdeepika]

@ieee8023 Thank you so much