Build bias weights for filter produces with `_summary_reshape`

Function used for rezooming high level feature maps. Uses bilinear interpolation to select all channels at index (x, y) for a high level feat

measure overlap between 3D bounding boxes, parametrized by (ry, h, w, l, tx, ty, tz)

Run one evaluation against the full epoch of data. Parameters ---------- hypes : dict Hyperparameters modules : tuble

Build the tensorflow graph out of the model files. Parameters ---------- hypes : dict Hyperparameters queue: tf.queue

General configuration values.

Continues training of a model. This will load model files and weights found in logdir and continues an aborted training. Parameters

Create a filewriter handler. A copy of the output will be written to logging_file. Parameters ---------- logging_file : string

Create Queues.

Apply decoder to the logits. Computation which decode CNN boxes. The output can be interpreted as bounding Boxes. Args: logits: L

Compute summary metrics for tensorboard

Overlay input_image with a hard segmentation result for two classes. Store the result with the same name as segmentation_image, but with

r""" Get the accuracy from a confusion matrix n. The mean accuracy is calculated as .. math:: t_i &= \sum_{j=1}^k n_{ij}\\

Get the distribution of classes in a labeled dataset. Parameters ---------- hypes : dict The hyperparameters have to specify

Get the distribution of colors of masks in a labeled dataset. Parameters ---------- labeled_dataset : list of dicts Each dic

Get the confuscation matrix of a segmentation image and its ground truth. The confuscation matrix is a detailed count of which classes i wer

Compute the F-beta score. The F(1) score is the harmonic mean of precision and recall. The worst value is 0, the best value is 1. `

Get frequency weighted intersection over union. Parameters ---------- n : dict Confusion matrix which has integer keys 0, ..

Get the mean accuracy from a confusion matrix n. Parameters ---------- n : dict Confusion matrix which has integer keys 0, .

Get mean intersection over union from a confusion matrix n. Parameters ---------- n : dict Confusion matrix which has intege

Get precision. Parameters ---------- n : dict Confusion matrix which has integer keys 0, ..., nb_classes - 1; an ent

Get recall. Parameters ---------- n : dict Confusion matrix which has integer keys 0, ..., nb_classes - 1; an entry

measure overlap between bird's eye view bounding boxes, parametrized by (ry, l, w, tx, tz)

criterion defines whether the overlap is computed with respect to both areas (ground truth and detection) or with respect to box a or b (detection and

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

Input: w: A 4D block tensor of shape (n, h, w, c) i: A list of 3-tuples [(x_1, y_1, z_1), (x_2, y_2, z_2), ...], each