--------------------------------------------------------------- @brief returns true, if group has no children, false otherwise */

Get the current evaluation result. Returns ------- name : str Name of the metric. value : float

@brief returns number of children */

--------------------------------------------------------------- @brief returns if a group/parameter is blocking/positional */

r"""Return location for the pretrained on local file system. This function will download from online model zoo when model cannot be found or has

--------------------------------------------------------------- @brief returns if a group/parameter is repeatable */

--------------------------------------------------------------- @brief returns mutating iterator to position of first element */

Returns a pre-defined model by name Parameters ---------- name : str Name of the model. pretrained : bool or str Bool

@brief returns mutating iterator to position one past the last element */

--------------------------------------------------------------- @brief returns if a parameter is required */

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

@brief returns if children are mutually exclusive alternatives */

Create directory recursively if not exists. Similar to `makedir -p`, you can skip checking existence before this function. Parameters ---

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

Get SSD models. Parameters ---------- name : str or None Model name, if `None` is used, you must specify `features` to be a `Hybr

@brief returns if a command line argument can be matched by a * combination of (partial) matches through any number of children */

@brief returns true if operators , & | and other combinating functions * will merge groups and false otherwise */

Download an given URL Parameters ---------- url : str URL to download path : str, optional Destination path to store d

:param params_shapes: dictionary of shapes of convolutional weights :param prefix: prefix of the original resnet50_v1d :param pretrained:

Set non-maximum suppression parameters. Parameters ---------- nms_thresh : float, default is 0.45. Non-maximum su

r"""MobileNet model from the `"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications" <https://arxiv.org/abs/1704

r"""AttentionModel model from `"Residual Attention Network for Image Classification" <https://arxiv.org/pdf/1704.06904.pdf>`_ paper. Para

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

Tricks to optionally install and import pycocotools

A common conv-bn-leakyrelu cell

Collect trainable params. This function serves as a help utility function to return only trainable parameters if predefined by experi

Visualize image. Parameters ---------- npimg : numpy.ndarray Single channel image with shape `H, W, 1`. dataset : str, defaul

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

Get YOLOV3 models. Parameters ---------- name : str or None Model name, if `None` is used, you must specify `features` to be a `Hy

r"""VGG model from the `"Very Deep Convolutional Networks for Large-Scale Image Recognition" <https://arxiv.org/abs/1409.1556>`_ paper. Param

Constructs a ResNetV1b-50 model. Parameters ---------- pretrained : bool or str Boolean value controls whether to load the defaul

Segmentation Datasets

Constructs a ResNetV1d-101 model. Parameters ---------- pretrained : bool or str Boolean value controls whether to load the defau

Returns stored target generator Returns ------- mxnet.gluon.HybridBlock The RCNN target generator

Updates the internal evaluation result. Parameters ---------- labels : list of `NDArray` The labels of the data wi

forwarding pre-trained network

Check whether the sha1 hash of the file content matches the expected hash. Parameters ---------- filename : str Path to the file.

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

r"""DeepLabV3 Parameters ---------- dataset : str, default pascal_voc The dataset that model pretrained on. (pascal_voc, ade20k)

r"""ResNext model from `"Aggregated Residual Transformations for Deep Neural Network" <http://arxiv.org/abs/1611.05431>`_ paper. Parameters

Loss forward

--------------------------------------------------------------- @brief returns either longest matching prefix of 'arg' in any * of the fl

Set mixup random sampler, use None to disable. Parameters ---------- mixup : callable random generator, e.g. np.random.unifor