Compute pairwise intersection areas between masks. Args: box_mask_list1: BoxMaskList holding N boxes and masks box_mask_list2: BoxMaskList

Compute pairwise intersection areas between boxes. Args: boxlist1: BoxList holding N boxes boxlist2: BoxList holding M boxes Returns:

Computes pairwise intersection-over-area between box collections. Intersection-over-area (ioa) between two boxes box1 and box2 is defined as thei

Computes pairwise intersection-over-area between box collections. Intersection-over-area (ioa) between two masks, mask1 and mask2 is defined as t

Computes pairwise intersection-over-union between box and mask collections. Args: box_mask_list1: BoxMaskList holding N boxes and masks box

Computes pairwise intersection-over-union between box collections. Args: boxes1: a numpy array with shape [N, 4] holding N boxes. boxes2: a

Computes pairwise intersection-over-union between box collections. Args: boxlist1: BoxList holding N boxes boxlist2: BoxList holding M boxe

Computes pairwise intersection-over-union between mask collections. Args: masks1: a numpy array with shape [N, height, width] holding N masks.

Adds color defined by the dataset colormap to the label. Args: label: A 2D array with integer type, storing the segmentation label. dataset

Loads categories from a csv file. The CSV file should have one comma delimited numeric category id and string category name pair per line. For ex

Manually stepped learning rate schedule. This function provides fine grained control over learning rates. One must specify a sequence of learnin

Matrix multiplication based implementation of the crop and resize op. Extracts crops from the input image tensor and bilinearly resizes them (pos

Matrix multiplication based implementation of tf.gather on zeroth axis. TODO(rathodv, jonathanhuang): enable sparse matmul option. Args: par

Gets mean pixel value. This function returns different mean pixel value, depending on the input model_variant which adopts different preprocessin

Merges boxes with same coordinates and returns K-hot encoded classes. Args: boxes: A tf.float32 tensor with shape [N, 4] holding N boxes. c

Updates `configs` dictionary based on supplied parameters. This utility is for modifying specific fields in the object detection configs. Say tha

Python function to merge numpy boxes.

Tiles the contents of x and y into a pair of grids. Multidimensional analog of numpy.meshgrid, giving the same behavior if x and y are vectors. G

Multi-class version of non maximum suppression. This op greedily selects a subset of detection bounding boxes, pruning away boxes that have high

Multi-class version of non maximum suppression. This op greedily selects a subset of detection bounding boxes, pruning away boxes that have high

Multiply gradients whose variable names match a regular expression. Args: grads_and_vars: A list of gradient to variable pairs (tuples). re

Nearest neighbor upsampling implementation. Nearest neighbor upsampling function that maps input tensor with shape [batch_size, height, width, ch

L2 normalizes the inputs across the specified dimension to a target norm. This op implements the L2 Normalization layer introduced in Liu, Wei, e

Converts a batch of boxes from normal to image coordinates. Args: normalized_boxes: a float32 tensor of shape [None, num_boxes, 4] in nor

Pad or clip the input tensor along the first dimension. Args: t: the input tensor, assuming the rank is at least 1. length: a tensor of sha

Pads the given image with the given pad_value. Works like tf.image.pad_to_bounding_box, except it can pad the image with any given arbitrary pad

Returns the tensor zero padded to the specified multiple. Appends 0s to the end of the first and second dimension (height and width) of the tenso

Returns a zero padded one-hot tensor. This function converts a sparse representation of indices (e.g., [4]) to a zero padded one-hot representati

Position-sensitive crop and pool rectangular regions from a feature grid. The output crops are split into `spatial_bins_y` vertical bins and `spa

模型预测 :param file_dir: 预测文件路径 :return:

Predicts segmentation labels. Args: images: A tensor of size [batch, height, width, channels]. model_options: A ModelOptions instance to co

Predicts segmentation labels. Args: images: A tensor of size [batch, height, width, channels]. model_options: A ModelOptions instance to co

Preprocesses the image and label. Args: image: Input image. label: Ground truth annotation label. crop_height: The height value used to

Prunes the boxes in boxlist1 that overlap less than thresh with boxlist2. For each box in boxlist1, we want its IOA to be more than minoverlap with

Prunes the boxes in list1 that overlap less than thresh with list2. For each mask in box_mask_list1, we want its IOA to be more than minoverlap w

Prunes bounding boxes that fall outside a given window. This function prunes bounding boxes that even partially fall outside the given window. Se

Crops the given list of images. The function applies the same crop to each image in the list. This can be effectively applied when there are mult

Randomly scales image and label. Args: image: Image with shape [height, width, 3]. label: Label with shape [height, width, 1]. scale: T

Read list of training or validation examples. The file is assumed to contain a single example per line where the first token in the line is an id

Recursively parses XML contents to python dict. We assume that `object` tags are the only ones that can appear multiple times at the same level o

Computes sum across all dimensions following first `ndims` dimensions.

Transforms the box masks back to full image masks. Embeds masks in bounding boxes of larger masks whose shapes correspond to image shape. Args

The default function when there are more than 0 box masks.

Replaces nan label scores with 1.0. Args: label_scores: a tensor containing object annoation label scores. Returns: a tensor where NaN l

Resizes image or label so their sides are within the provided range. The output size can be described by two cases: 1. If the image can be rescal

Resnet v1 101. Args: inputs: A tensor of size [batch, height_in, width_in, channels]. num_classes: Number of predicted classes for classifi

Resnet v1 101 beta variant. This variant modifies the first convolution layer of ResNet-v1-101. In particular, it changes the original one 7x7 co

Resnet v1 50. Args: inputs: A tensor of size [batch, height_in, width_in, channels]. num_classes: Number of predicted classes for classific

Resnet v1 50 beta variant. This variant modifies the first convolution layer of ResNet-v1-50. In particular, it changes the original one 7x7 conv

Retains only groundtruth with positive class ids. Args: tensor_dict: a dictionary of following groundtruth tensors - fields.InputDataFiel

Gets root_block_fn for beta variant. ResNet-v1 beta variant modifies the first original 7x7 convolution to three 3x3 convolutions. Args: n

Saves the given label to image on disk. Args: label: The numpy array to be saved. The data will be converted to uint8 and saved as png im

Saves categories to a csv file. Args: categories: A list of dictionaries representing categories to save to file. Each category

Saves an image (represented as a numpy array) to PNG. Args: image: a numpy array with shape [height, width, 3]. output_path: path to which

Saves a pipeline config text file to disk. Args: pipeline_config: A pipeline_pb2.TrainEvalPipelineConfig. directory: The model directory in

Decorator that scopes a function with its name. Useful for the graph visualization of Tensorboard. :param func: :param args: