since some stages won't see partial anchors, so we have to slice the correct targets

--------------------------------------------------------------- @brief returns true if all children is blocking */

evaluating network with inputs and targets

/ * @brief forwards string to first non-whitespace char; * std string -> unsigned conv yields max value, but we want 0; * also checks

r"""FCN model from the paper `"Fully Convolutional Network for semantic segmentation" <https://people.eecs.berkeley.edu/~jonlong/long_shelhamer_fc

r"""Pyramid Scene Parsing Network Parameters ---------- dataset : str, default pascal_voc The dataset that model pretrained on. (p

--------------------------------------------------------------- @brief returns longest common prefix of all flags */

Helper function to export a HybridBlock to symbol JSON to be used by `SymbolBlock.imports`, `mxnet.mod.Module` or the C++ interface.. Paramet

r"""Densenet-BC model from the `"Densely Connected Convolutional Networks" <https://arxiv.org/pdf/1608.06993.pdf>`_ paper. Parameters ---

r"""Utility function to return mask rcnn networks. Parameters ---------- name : str Model name. dataset : str The nam

r"""MobileNetV2 model from the `"Inverted Residuals and Linear Bottlenecks: Mobile Networks for Classification, Detection and Segmentation"

r"""NASNet A model from `"Learning Transferable Architectures for Scalable Image Recognition" <https://arxiv.org/abs/1707.07012>`_ paper

r"""Update the training history Parameters --------- labels: list of str List of label names to plot. col

Try import cv2 at runtime. Returns ------- cv2 module if found. Raise ImportError otherwise

@brief go to new line, and start a new paragraph */

Parse network with specified outputs and other arguments. Parameters ---------- network : str or HybridBlock or Symbol Logic chai

Print summary of certain result map.

@brief returns true if all children are optional (=non-required) */

@brief position of the match within the subject string */

Darknet v3 53 layer network. Reference: https://arxiv.org/pdf/1804.02767.pdf. Parameters ---------- norm_layer : object Norma

A logger used to output seed information to nosetests logs.

/ * * @brief prints first flag or value label of a parameter * *****************************************************************************/

r"""ResNet V1 model from `"Deep Residual Learning for Image Recognition" <http://arxiv.org/abs/1512.03385>`_ paper. ResNet V2 model from `"Ide

Try import the specified package. If the package not installed, try use pip to install and import if success. Parameters ---------- p

--------------------------------------------------------------- @brief returns recursive parameter count */

Reset class categories and class predictors. Parameters ---------- classes : iterable of str The new categories. [

convert color from hsv to bgr for plotting

Parse xml file and return labels.

Assign rpn_rois to specific FPN layers according to its area and then perform `ROIPooling` or `ROIAlign` to generate final regio

Use coco to get real scores.

@brief returns if all children are value parameters (recursive) */