Skip to content

Validation loss calculation (supposedly) breaks training  #31

Description

@404ic

When running the training code, in a couple iterations it says the cost matrix is infeasible based on linear_sum_assignment in multibox_detection/loss.py When I remove all the code from train_detection.py that calculates the validation loss, the training works.

Also noticed that when val_loss is computed, batch_size is passed as tf.get_shape(locs_v)[0] which doesn't give the batch size, but changing it to locs_v.get_shape().as_list()[0] should work.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions