Set the input(s) for the next operation by replacing the terminal nodes. The arguments can be either layer names or the actual layers.

Load network weights. data_path: The path to the numpy-serialized network weights session: The current TensorFlow session igno

Creates a new TensorFlow variable.

Calibrate bounding boxes

Compute the padding coordinates (pad the bounding boxes to square)

Convert bboxA to square.

Use heatmap to generate bounding boxes

Verifies that the padding is one of the supported ones.

Add summaries for losses. Generates moving average for all losses and associated summaries for visualizing the performance of the network.

Builds the 8x8 resnet block.

Builds the 8x8 resnet block.

Returns an index-suffixed unique name for the given prefix. This is used for auto-generating layer names based on the type-prefix.

Creates the Inception Resnet V1 model. Args: inputs: a 4-D tensor of size [batch_size, height, width, 3]. num_classes: number of predi

Creates the Inception Resnet V2 model. Args: inputs: a 4-D tensor of size [batch_size, height, width, 3]. num_classes: number of predi

Select the triplets for training

Construct the network.

Builds the 17x17 resnet block.

Builds the 17x17 resnet block.

Builds the 35x35 resnet block.

Builds the 35x35 resnet block.

Detects faces in a list of images images: list containing input images detection_window_size_ratio: ratio of minimum face size to smallest ima

Center loss based on the paper "A Discriminative Feature Learning Approach for Deep Face Recognition" (http://ydwen.github.io/papers/WenECCV16.

Detects faces in an image, and returns bounding boxes and points for them. img: input image minsize: minimum faces' size pnet, rnet, onet:

Returns the current network output.