Prints a text message. And, optionally, if a Numpy array is provided it prints it's shape, min, and max values.

Prints a text message. And, optionally, if a Numpy array is provided it prints it's shape, min, and max values.

Draws mask on an image. Args: image: uint8 numpy array with shape (img_height, img_height, 3) mask: a uint8 numpy array of shape (img_heigh

Adds a bounding box to an image (numpy array). Args: image: a numpy array with shape [height, width, 3]. ymin: ymin of bounding box in norm

Draws keypoints on an image (numpy array). Args: image: a numpy array with shape [height, width, 3]. keypoints: a numpy array with shape [n

Prints a text message. And, optionally, if a Numpy array is provided it prints it's shape, min, and max values.

The identity_block is the block that has no conv layer at shortcut # Arguments input_tensor: input tensor kernel_size: defualt 3,

The identity_block is the block that has no conv layer at shortcut # Arguments input_tensor: input tensor kernel_size: default 3,

The identity_block is the block that has no conv layer at shortcut # Arguments input_tensor: input tensor kernel_size: default 3,

Prediction tensors from inputs tensor. Args: preprocessed_inputs: a [batch, 28, 28, channels] float32 tensor. true_image_shapes: int3

Build Mask R-CNN architecture. input_shape: The shape of the input image. mode: Either "training" or "inference". The inputs a

Train the model. train_dataset, val_dataset: Training and validation Dataset objects. learning_rate: The learning rate to train with

Apply the given mask to the image.

Apply the given mask to the image.

Display Configuration values.

mode: Either "training" or "inference" config: A Sub-class of the Config class model_dir: Directory to save training logs and

mode: Either "training" or "inference" config: A Sub-class of the Config class model_dir: Directory to save training logs and

mode: Either "training" or "inference" config: A Sub-class of the Config class model_dir: Directory to save training logs and

Apply the given mask to the image.

Apply the given mask to the image.

conv_block is the block that has a conv layer at shortcut # Arguments input_tensor: input tensor kernel_size: defualt 3, the kerne

conv_block is the block that has a conv layer at shortcut # Arguments input_tensor: input tensor kernel_size: default 3, the kerne

conv_block is the block that has a conv layer at shortcut # Arguments input_tensor: input tensor kernel_size: default 3, the kerne

Returns anchor pyramid for the given image size.

Returns anchor pyramid for the given image size.

Load a subset of the COCO dataset. dataset_dir: The root directory of the COCO dataset. subset: What to load (train, val, minival, val

Generate random colors. To get visually distinct colors, generate them in HSV space then convert to RGB.

Generate random colors. To get visually distinct colors, generate them in HSV space then convert to RGB.

Generate random colors. To get visually distinct colors, generate them in HSV space then convert to RGB.

Generate random colors. To get visually distinct colors, generate them in HSV space then convert to RGB.

Overlay labeled boxes on an image with formatted scores and label names. This function groups boxes that correspond to the same location and crea

Gets the model ready for training. Adds losses, regularization, and metrics. Then calls the Keras compile() function.

Gets the model ready for training. Adds losses, regularization, and metrics. Then calls the Keras compile() function.

Runs the detection pipeline. images: List of images, potentially of different sizes. Returns a list of dicts, one dict per image. Th

Runs the detection pipeline. images: List of images, potentially of different sizes. Returns a list of dicts, one dict per image. Th

Display Configuration values.

Modified version of the correspoding Keras function with the addition of multi-GPU support and the ability to exclude some layers from

Modified version of the corresponding Keras function with the addition of multi-GPU support and the ability to exclude some layers fro

Converts boxes from pixel coordinates to normalized coordinates. boxes: [..., (y1, x1, y2, x2)] in pixel coordinates shape: [..., (height, wid

Converts boxes from pixel coordinates to normalized coordinates. boxes: [..., (y1, x1, y2, x2)] in pixel coordinates shape: [..., (height, wid

Parses a tensor that contains image attributes to its components. See compose_image_meta() for more details. meta: [batch, meta length] where

Parses a tensor that contains image attributes to its components. See compose_image_meta() for more details. meta: [batch, meta length] where

Prepares the Dataset class for use. TODO: class map is not supported yet. When done, it should handle mapping classes from diff

Input preprocessing, resizes images to 28x28. Args: inputs: a [batch, height_in, width_in, channels] float32 tensor representing a

Applies the given deltas to the given boxes. boxes: [N, 4] where each row is y1, x1, y2, x2 deltas: [N, 4] where each row is [dy, dx, log(dh),

Applies the given deltas to the given boxes. boxes: [N, (y1, x1, y2, x2)] boxes to update deltas: [N, (dy, dx, log(dh), log(dw))] refinements

Applies the given deltas to the given boxes. boxes: [N, (y1, x1, y2, x2)] boxes to update deltas: [N, (dy, dx, log(dh), log(dw))] refinements

Builds the computation graph of the mask head of Feature Pyramid Network. rois: [batch, num_rois, (y1, x1, y2, x2)] Proposal boxes in normalized

Builds the computation graph of the mask head of Feature Pyramid Network. rois: [batch, num_rois, (y1, x1, y2, x2)] Proposal boxes in normalized

Builds the computation graph of the mask head of Feature Pyramid Network. rois: [batch, num_rois, (y1, x1, y2, x2)] Proposal boxes in normalized

boxes: [N, 4] each row is y1, x1, y2, x2 window: [4] in the form y1, x1, y2, x2

boxes: [N, (y1, x1, y2, x2)] window: [4] in the form y1, x1, y2, x2

boxes: [N, (y1, x1, y2, x2)] window: [4] in the form y1, x1, y2, x2

Apply color splash effect. image: RGB image [height, width, 3] mask: instance segmentation mask [height, width, instance count] Returns r

Apply color splash effect. image: RGB image [height, width, 3] mask: instance segmentation mask [height, width, instance count] Returns r

Gets the model ready for training. Adds losses, regularization, and metrics. Then calls the Keras compile() function.

Takes attributes of an image and puts them in one 1D array. image_id: An int ID of the image. Useful for debugging. image_shape: [height, wid

Takes attributes of an image and puts them in one 1D array. image_id: An int ID of the image. Useful for debugging. original_image_shape: [H,

Takes attributes of an image and puts them in one 1D array. image_id: An int ID of the image. Useful for debugging. original_image_shape: [H,

Computes the width and height of each stage of the backbone network. Returns: [N, (height, width)]. Where N is the number of stages

Computes the width and height of each stage of the backbone network. Returns: [N, (height, width)]. Where N is the number of stages

Calculates IoU of the given box with the array of the given boxes. box: 1D vector [y1, x1, y2, x2] boxes: [boxes_count, (y1, x1, y2, x2)]

Calculates IoU of the given box with the array of the given boxes. box: 1D vector [y1, x1, y2, x2] boxes: [boxes_count, (y1, x1, y2, x2)]

Calculates IoU of the given box with the array of the given boxes. box: 1D vector [y1, x1, y2, x2] boxes: [boxes_count, (y1, x1, y2, x2)]

A generator that returns images and corresponding target class ids, bounding box deltas, and masks. dataset: The Dataset object to pick data

A generator that returns images and corresponding target class ids, bounding box deltas, and masks. dataset: The Dataset object to pick data

A generator that returns images and corresponding target class ids, bounding box deltas, and masks. dataset: The Dataset object to pick data

Runs the detection pipeline. images: List of images, potentially of different sizes. Returns a list of dicts, one dict per image. Th

Display Configuration values.

Adds a bounding box to an image. Each string in display_str_list is displayed on a separate line above the bounding box in black text on a rectan

Builds the computation graph of the feature pyramid network classifier and regressor heads. rois: [batch, num_rois, (y1, x1, y2, x2)] Proposa

Builds the computation graph of the feature pyramid network classifier and regressor heads. rois: [batch, num_rois, (y1, x1, y2, x2)] Proposa

Builds the computation graph of the feature pyramid network classifier and regressor heads. rois: [batch, num_rois, (y1, x1, y2, x2)] Proposa

Returns a list of layers that have weights.

Load a subset of the Balloon dataset. dataset_dir: Root directory of the dataset. subset: Subset to load: train or val

Load a subset of the Balloon dataset. dataset_dir: Root directory of the dataset. subset: Subset to load: train or val

Load the specified image and return a [H,W,3] Numpy array.

Load and return ground truth data for an image (image, mask, bounding boxes). augment: (deprecated. Use augmentation instead). If true, apply ran

Load and return ground truth data for an image (image, mask, bounding boxes). augment: (deprecated. Use augmentation instead). If true, apply ran

Loads label map proto. Args: path: path to StringIntLabelMap proto text file. Returns: a StringIntLabelMapProto

Modified version of the corresponding Keras function with the addition of multi-GPU support and the ability to exclude some layers fro

Compute scalar loss tensors with respect to provided groundtruth. Calling this function requires that groundtruth tensors have been provided

Takes RGB images with 0-255 values and subtraces the mean pixel and converts it to float. Expects image colors in RGB order.

Expects an RGB image (or array of images) and subtracts the mean pixel and converts it to float. Expects image colors in RGB order.

Expects an RGB image (or array of images) and subtracts the mean pixel and converts it to float. Expects image colors in RGB order.

Takes a list of images and modifies them to the format expected as an input to the neural network. images: List of image matricies [he

Takes a list of images and modifies them to the format expected as an input to the neural network. images: List of image matrices [hei

Takes a list of images and modifies them to the format expected as an input to the neural network. images: List of image matrices [hei

Computes IoU overlaps between two sets of boxes. boxes1, boxes2: [N, (y1, x1, y2, x2)].

Computes IoU overlaps between two sets of boxes. boxes1, boxes2: [N, (y1, x1, y2, x2)].

Computes IoU overlaps between two sets of boxes. boxes1, boxes2: [N, (y1, x1, y2, x2)].

Parses a tensor that contains image attributes to its components. See compose_image_meta() for more details. meta: [batch, meta length] where

Prepares the Dataset class for use. TODO: class map is not supported yet. When done, it should handle mapping classes from diff

Prepares the Dataset class for use. TODO: class map is not supported yet. When done, it should handle mapping classes from diff

Sets the model log directory and epoch counter. model_path: If None, or a format different from what this code uses then set a ne

Sets the model log directory and epoch counter. model_path: If None, or a format different from what this code uses then set a ne