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

Returns a string representation for the given value.

Creates a new TensorFlow variable.

Verifies that the padding is one of the supported ones.

Load trained weights. Args: saver: TensorFlow saver object. sess: TensorFlow session. ckpt_path: path to checkpoint file wi

Resize masks and perform one-hot encoding. Args: input_batch: input tensor of shape [batch_size H W 1]. new_size: a tensor with new h

Load the layer definitions from the prototxt.

Returns key=formatted(value).

Calculate the average gradient for each shared variable across all towers. Note that this function provides a synchronization point across all tower

Builds the graph from the Caffe layer definitions.

crop and save image

Decode batch of segmentation masks. Args: mask: result of inference after taking argmax. num_images: number of images to decode f

Pack images and labels into a batch. Args: num_elements: the batch size. Returns: Two tensors

Emits the Python source for this node.

Filter out layers based on the current phase.

Translates Caffe's numeric padding to one of ('SAME', 'VALID'). Caffe supports arbitrary padding values, while TensorFlow only supports 'SAME'

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

Randomly mirrors the images. Args: img: Training image to mirror. label: Segmentation mask to mirror.

Returns true if this parent/child pair is eligible for fusion.

Create the model and start the evaluation process.

Create the model and start the evaluation process.

Create data input nodes. This method is for old-style inputs, where the input specification was not treated as a first-class

Create a graph node for the given layer.

Merge the child node into the parent.

find the largest square

Randomly crop and pads the input images. Args: image: Training image to crop/ pad. label: Segmentation mask to crop/ pad.

Read one image and its corresponding mask with optional pre-processing. Args: input_queue: tf queue with paths to the image and its mas

Read one image and its corresponding mask with optional pre-processing. Args: input_queue: tf queue with paths to the image and its mas

Reads txt file containing paths to images and ground truth masks. Args: data_dir: path to the directory with images and masks. da

Reads txt file containing paths to images and ground truth masks. Args: data_dir: path to the directory with images and masks. da

Save weights. Args: saver: TensorFlow Saver object. sess: TensorFlow session. logdir: path to the snapshots directory. step

Construct the network.