Select a 2d convolution implementation based on arguments Creates and returns one of torch.nn.Conv2d, Conv2dSame, MixedConv2d, or CondConv2d.

Sample positive and negative bboxes. This is a simple implementation of bbox sampling given candidates, assigning results and ground

Start the timer.

Convert detection results to a list of numpy arrays. Args: bboxes (Tensor): shape (n, 5) labels (Tensor): shape (n, ) num

Select a 2d convolution implementation based on arguments Creates and returns one of torch.nn.Conv2d, Conv2dSame, MixedConv2d, or CondConv2d.

Round number of filters based on depth multiplier.

Creates a stack of inverted residuals.

Generate bbox and apply lambda correction.

Decode segmentation class labels into a color image Args: label_mask (np.ndarray): an (M,N) array of integer values denoting the

Get segmentation masks from mask_pred and bboxes. Args: mask_pred (Tensor or ndarray): shape (n, #class+1, h, w).

Unmap a subset of item (data) back to the original set of items (of size count)

Creates an EfficientNet-CondConv model. Ref impl: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet/condconv

Creates an EfficientNet-EdgeTPU model Ref impl: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet/edgetpu

Creates a MixNet Medium-Large model. Ref impl: https://github.com/tensorflow/tpu/tree/master/models/official/mnasnet/mixnet Paper: https://ar

Average latest n values or all values

Select a 2d convolution implementation based on arguments Creates and returns one of torch.nn.Conv2d, Conv2dSame, MixedConv2d, or CondConv2d.

Select a 2d convolution implementation based on arguments Creates and returns one of torch.nn.Conv2d, Conv2dSame, MixedConv2d, or CondConv2d.

Returns a dictionary containing a whole state of the module. Both parameters and persistent buffers (e.g. running averages) are included. Key

piecewise index function defined in Eq. (18) in our paper. Parameters ---------- relative_position: torch.Tensor, dtype: long or float

piecewise index function defined in Eq. (18) in our paper. Parameters ---------- relative_position: torch.Tensor, dtype: long or float

piecewise index function defined in Eq. (18) in our paper. Parameters ---------- relative_position: torch.Tensor, dtype: long or float

make DAG plot and save to file_path as .png

Print a log message. Args: msg (str): The message to be logged. logger (logging.Logger | str | None): The logger to be used. Some

Round number of filters based on depth multiplier.