Adds groundtruth for a single image to be used for evaluation. Args: image_id: A unique string/integer identifier for the image. grou

Adds groundtruth for a single image to be used for evaluation. Args: image_key: A unique string/integer identifier for the image. gro

Adds softmax cross entropy loss for logits of each scale. Args: scales_to_logits: A map from logits names for different scales to logits.

Computes area of masks. Args: box_mask_list: np_box_mask_list.BoxMaskList holding N boxes and masks Returns: a numpy array with shape [N

Asserts that shape_a and shape_b are equal. If the shapes are static, raises a ValueError when the shapes mismatch. If the shapes are dynamic,

Asserts that shape_a and shape_b are the same along the 0th-dimension. If the shapes are static, raises a ValueError when the shapes mismatch.

Bottleneck residual unit variant with BN after convolutions. This is the original residual unit proposed in [1]. See Fig. 1(a) of [2] for its def

Numpy function to plot CDF.

Change coordinate frame of the boxlist to be relative to window's frame. Given a window of the form [ymin, xmin, ymax, xmax], changes bounding bo

Checks that the image width/height are greater than some number. This function is used to check that the width and height of an image are above a

Clears the state to prepare for a fresh evaluation.

Clears stored data.

Clip bounding boxes to a window. This op clips input bounding boxes (represented by bounding box corners) to a window, optionally filtering out b

Returns a list containing static and dynamic values for the dimensions. Returns a list of static and dynamic values for shape dimensions. This is

Compute Average Precision according to the definition in VOCdevkit. Precision is modified to ensure that it does not decrease as recall decrease.

Compute CorLoc according to the definition in the following paper. https://www.robots.ox.ac.uk/~vgg/rg/papers/deselaers-eccv10.pdf Returns nans

Computes MedianRank@k, where k is the top-scoring labels. Args: tp_fp_list: a list of numpy arrays; each numpy array corresponds to the all

Compute precision and recall. Args: scores: A float numpy array representing detection score labels: A float numpy array representing weigh

Computes Recall@k, MedianRank@k, where k is the top-scoring labels. Args: tp_fp_list: a list of numpy arrays; each numpy array corresponds to t

Concatenate list of box_mask_lists. This op concatenates a list of input box_mask_lists into a larger box_mask_list. It also handles concatena

Cosine decay schedule with warm up period. Cosine annealing learning rate as described in: Loshchilov and Hutter, SGDR: Stochastic Gradient Des

Reads a label map and returns a category index. Args: label_map_path: Path to `StringIntLabelMap` proto text file. Returns: A category i

Creates a category index with a single `object` class.

Creates pyramid image. Useful for testing. For example, pyramid_image(5, 6, 1) looks like: # [[[ 5. 4. 3. 2. 1. 0.] # [ 6. 5. 4. 3.

Creates a pipeline_pb2.TrainEvalPipelineConfig from configs dictionary. This function performs the inverse operation of create_configs_from_pipel

Creates random bounding boxes of specific maximum height and width. Args: num_boxes: number of boxes. max_height: maximum height of boxes.

Convenient function for deleting a word.

Converts bounding boxes from dense to sparse form. Args: dense_locations: a [max_num_boxes, 4] tensor in which only the first k rows are

Draws bounding boxes on image (numpy array). Args: image: a numpy array object. boxes: a 2 dimensional numpy array of [N, 4]: (ymin, xmin,

Draws boxes on image.

Creates a side-by-side image with detections and groundtruth. Bounding boxes (and instance masks, if available) are visualized on both subimages.

Change the module's `cut` and `cut_for_search` functions to the parallel version. Note that this only works using dt, custom Tokenizer

Encodes a numpy array into a PNG string. Args: image: a numpy array with shape [height, width, 3]. Returns: PNG encoded image string.

Computes evaluation result. Returns: A named tuple with the following fields - average_precision: a float number corresponding to a

Compute evaluation result. Returns: A dictionary of metrics with the following fields - 1. summary_metrics: 'Precision/mAP@<

Compute evaluation result. Returns: A named tuple with the following fields - average_precision: float numpy array of average preci

Exponential decay schedule with burn-in period. In this schedule, learning rate is fixed at burnin_learning_rate for a fixed period, before trans

Extracts features by the particular model_variant. Args: images: A tensor of size [batch, height, width, channels]. output_stride: The rati

Extract keywords from sentence using TF-IDF algorithm. Parameter: - topK: return how many top keywords. `None` for all po

Filters out groundtruth with boxes corresponding to crowd. Args: tensor_dict: a dictionary of following groundtruth tensors - fields.Inpu

Filters out groundtruth with no bounding boxes. Args: tensor_dict: a dictionary of following groundtruth tensors - fields.InputDataFields

Checks if first K entries of two lists are close, up to permutation. Inputs to this assert are lists of items which can be compared via numpy.all

Pads the input along the spatial dimensions independently of input size. Args: inputs: A tensor of size [batch, height_in, width_in, channels].

Randomly flips a dimension of the given tensor. The decision to randomly flip the `Tensors` is made together. In other words, all or none of the

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

Gets the dataset split for semantic segmentation. This functions gets the dataset split for semantic segmentation. In particular, it is a wrapper

Returns batch size from the tensor shape. Args: tensor_shape: A rank 4 TensorShape. Returns: An integer representing the batch size of t

Reads training configuration from multiple config files. Args: model_config_path: Path to model_pb2.DetectionModel. train_config_path: Path

Reads config from a file containing pipeline_pb2.TrainEvalPipelineConfig. Args: pipeline_config_path: Path to pipeline_pb2.TrainEvalPipelineCon

Gets an instance of slim Dataset. Args: dataset_name: Dataset name. split_name: A train/val Split name. dataset_dir: The directory of t

Returns depth from the tensor shape. Args: tensor_shape: A rank 4 TensorShape. Returns: An integer representing the depth of the tensor.

Gets the scopes for extra layers. Args: last_layers_contain_logits_only: Boolean, True if only consider logits as the last layer (i.e., exc

Returns height from the tensor shape. Args: tensor_shape: A rank 4 TensorShape. Returns: An integer representing the height of the tenso

Returns the image resizer config from a model config. Args: model_config: A model_pb2.DetectionModel. Returns: An image_resizer_pb2.Imag

Reads a label map and returns a dictionary of label names to id. Args: label_map_path: path to label_map. use_display_name: whether to use

Get maximum index in label map. Args: label_map: a StringIntLabelMapProto Returns: an integer

Gets the gradient multipliers. The gradient multipliers will adjust the learning rates for model variables. For the task of semantic segmentation

Gets the function initializing model variables from a checkpoint. Args: train_logdir: Log directory for training. tf_initial_checkpoint: Te

Gets model's learning rate. Computes the model's learning rate for different learning policy. Right now, only "step" and "poly" are supported.

Returns the number of classes for a detection model. Args: model_config: A model_pb2.DetectionModel. Returns: Number of classes. Rais

Gets a random scale value. Args: min_scale_factor: Minimum scale value. max_scale_factor: Maximum scale value. step_size: The step size

Returns expected spatial size of the output image from a given config. Args: image_resizer_config: An image_resizer_pb2.ImageResizer. Return

Returns the subset of variables available in the checkpoint. Inspects given checkpoint and returns the subset of variables that are available in

Returns width from the tensor shape. Args: tensor_shape: A rank 4 TensorShape. Returns: An integer representing the width of the tensor.

Numpy function to plot hist.

Converts one image/segmentation pair to tf example. Args: image_data: string of image data. filename: image filename. height: image hei

Creates dense vector with indices set to specific value and rest to zeros. This function exists because it is unclear if it is safe to use tf.s