tfm.vision.layers.BoxSampler

Creates a BoxSampler to sample positive and negative boxes.

tfm.vision.layers.BoxSampler(
    num_samples: int = 512, foreground_fraction: float = 0.25, **kwargs
)

Args
`num_samples`	An `int` of the number of sampled boxes per image.
`foreground_fraction`	A `float` in [0, 1], what percentage of boxes should be sampled from the positive examples.
`**kwargs`	Additional keyword arguments passed to Layer.

Methods

call(
    positive_matches: tf.Tensor,
    negative_matches: tf.Tensor,
    ignored_matches: tf.Tensor
)

Samples and selects positive and negative instances.

Args
`positive_matches`	A `bool` tensor of shape of [batch, N] where N is the number of instances. For each element, `True` means the instance corresponds to a positive example.
`negative_matches`	A `bool` tensor of shape of [batch, N] where N is the number of instances. For each element, `True` means the instance corresponds to a negative example.
`ignored_matches`	A `bool` tensor of shape of [batch, N] where N is the number of instances. For each element, `True` means the instance should be ignored.

Returns
A `tf.tensor` of shape of [batch_size, K], storing the indices of the sampled examples, where K is `num_samples`.