Shortcuts

caer.preprocessing

caer.preprocessing.compute_mean(data, channels, per_channel_subtraction=True)[source]

Computes mean per channel over the train set and returns a tuple of dimensions=channels Train should not be normalized

Return type

Tuple

caer.preprocessing.compute_mean_from_dir(DIR, channels, per_channel_subtraction=True, recursive=True)[source]

Computes mean per channel Mean must be computed ONLY on the train set

Return type

Tuple

caer.preprocessing.subtract_mean(data, channels, mean_sub_values)[source]

Per channel subtraction values computed from compute_mean() or compute_mean_from_dir() Subtracts mean from the validation set

Return type

List[str]

Read the Docs v: latest
Versions
latest
stable
Downloads
pdf
On Read the Docs
Project Home
Builds

Free document hosting provided by Read the Docs.