Draws a caffe net and returns the image string encoded using the given extension. Parameters ---------- caffe_net : a caffe.proto.caf

Creates an image embedded in HTML base64 format.

Controls whether events will be forwarded to listeners_. Set to false in death test child processes.

Define edge label based on layer type.

Parse GPU ids or use all available devices

Define node label based on layer type. Parameters ---------- layer : ? rankdir : {'LR', 'TB', 'BT'} Direction of graph layout

Get year from log file system timestamp

Get dictionary mapping pooling type number to type name

Create a data structure which represents the `caffe_net`. Parameters ---------- caffe_net : object rankdir : {'LR', 'TB', 'BT'}

Find start time from group of lines

Invert a coord map by de-scaling and un-shifting; this gives the backward mapping for the gradient.

Returns true iff this is NAN (not a number).

Load the next image in a batch.

This code is borrowed from Ross Girshick's FAST-RCNN code (https://github.com/rbgirshick/fast-rcnn). It parses the PASCAL .xml metadata f

Gets the message associated with the test part.

@brief Input and output blob numbers

Find out the correspondence between layer names and parameter names.

Parse input arguments

Parse log file Returns (train_dict_list, train_dict_names, test_dict_list, test_dict_names) train_dict_list and test_dict_list are lists of d

preprocess() emulate the pre-processing occuring in the vgg16 caffe prototxt.

Ouput some info regarding the class

Print a simple nicely-aligned table. table must be a list of (equal-length) lists. Columns are space-separated, and as narrow as possible, bu

Usage: caffe_('reset')

Takes an image name, resize it and crop the center square

Resize an image array with interpolation. Parameters ---------- im : (H x W x K) ndarray new_dims : (height, width) tuple of new

Save CSV files to output_dir If the input log file is, e.g., caffe.INFO, the names will be caffe.INFO.train and caffe.INFO.test

* @brief Sets the loss associated with a top blob at a given index. */

STL-style container methods.

Parse command line options and start the server.

Gets the number of successful tests.

Test: score a model.

Returns the number of the test properties.

Time: benchmark the execution time of a model.

Generate a NetParameter that contains all layers needed to compute this top.

Gets the number of all test parts. This is the sum of the number of successful test parts and the number of failed test parts.

The constructor of SingleFailureChecker remembers where to look up test part results, what type of failure we expect, and what substring the failure m

* @param param provides AccuracyParameter accuracy_param, * with AccuracyLayer options: * - top_k (\b optional, default 1). * Sets

Adds a creator.

Adds a creator.