A little wrapper around tf.get_variable to do weight decay and add to

Helper to create summaries for activations. Creates a summary that provides a histogram of activations. Creates a summary that measure the sp

Return a data generator that outputs image samples. @ Returns image: integer array of shape [height, width, 3]. Representing RGB value of

Create Queues.

Changes RGB [0,1] valued image to BGR [0,255] with mean subtracted.

Take the data_file and hypes and create a generator. The generator outputs the image and the gt_image.

:param evalDict: :param tag:

:param evalDict: :param tag:

Recursive dict merge. Inspired by :meth:``dict.update()``, instead of updating only top-level keys, dict_merge recurses down into dicts nested

Analyze a trained model. This will load model files and weights found in logdir and run a basic analysis. Parameters ----------

.

Get location of `data_dir` and `run_dir'. Defaut is ./DATA and ./RUNS. Alternativly they can be set by the environoment variabels 'T

Generate Inputs images.

main.

Splits the Images in train and test. Assumes a File all.txt in data_folder.

@param ax:

@param ax:

Take each Line2D in the axes, ax, and convert the line style to be suitable for black and white viewing.

Take each Line2D in the axes, ax, and convert the line style to be suitable for black and white viewing.

Take each axes in the figure, and for each line in the axes, make the line viewable in black and white.

Take each axes in the figure, and for each line in the axes, make the line viewable in black and white.

Start enqueuing threads.

Returns an initializer that creates filter for bilinear upsampling. Use a transposed convolution layer with ksize = 2n and stride = n to perf

Initializer function.

Apply decoder to the logits. Args: logits: Logits tensor, float - [batch_size, NUM_CLASSES]. Return: logits: the logits are alre

Does the basic pixel based evaluation! :param gtBin: :param cur_prob: :param thres: :param validMap:

Does the basic pixel based evaluation! :param gtBin: :param cur_prob: :param thres: :param validMap:

Evaluate the quality of the logits at predicting the label. Args: logits: Logits tensor, float - [batch_size, NUM_CLASSES]. labels: L

Evaluate the quality of the logits at predicting the label. Args: logits: Logits tensor, float - [batch_size, NUM_CLASSES]. labels: L

Returns the ground truth maps for roadArea and the validArea :param fileNameGT:

Build the MNIST model up to where it may be used for inference. Args: images: Images placeholder, from inputs(). train: whether the n

Calculate the loss from the logits and the labels. Args: logits: Logits tensor, float - [batch_size, NUM_CLASSES]. labels: Labels ten

Calculate the loss from the logits and the labels. Args: logits: Logits tensor, float - [batch_size, NUM_CLASSES]. labels: Labels ten

Run main function.

Downloads, extracts and prepairs data.

:param in_image: :param conf: :param vis_channel: :param threshold:

:param in_image: :param conf: :param vis_channel: :param threshold:

Overlay original_image with segmentation_image. Parameters ----------

:param precision: :param recall: :param outFileName: :param Fig: :param drawCol: :param textLabel: :param fontsize1:

:param precision: :param recall: :param outFileName: :param Fig: :param drawCol: :param textLabel: :param fontsize1:

@param totalPosNum: scalar @param totalNegNum: scalar @param totalFN: vector @param totalFP: vector @param thresh: vector

@param totalPosNum: scalar @param totalNegNum: scalar @param totalFN: vector @param totalFP: vector @param thresh: vector

Replace the values in segmentation to the values defined in color_changes. Parameters ---------- segmentation : numpy array

:param data: :param outputname: :param cmap:

:param data: :param outputname: :param cmap:

Sets up the training Ops. Creates a summarizer to track the loss over time in TensorBoard. Creates an optimizer and applies the gradients to