Returns a list of layers that have weights.

Returns a list of layers that have weights.

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

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: If true, apply random image augmentation. Currently, only

Load instance masks for the given image. Different datasets use different ways to store masks. Override this method to load instance

Load instance masks for the given image. Different datasets use different ways to store masks. Override this method to load instance

Load instance masks for the given image. Different datasets use different ways to store masks. Override this method to load instance

Implementatin of Log2. TF doesn't have a native implemenation.

Implementation of Log2. TF doesn't have a native implementation.

Implementation of Log2. TF doesn't have a native implementation.

Creates a new wrapper model that consists of multiple replicas of the original model placed on different GPUs.

Creates a new wrapper model that consists of multiple replicas of the original model placed on different GPUs.

Takes a source class ID and returns the int class ID assigned to it. For example: dataset.map_source_class_id("coco.12") -> 23

Loss for Mask R-CNN bounding box refinement. target_bbox: [batch, num_rois, (dy, dx, log(dh), log(dw))] target_class_ids: [batch, num_rois].

Loss for Mask R-CNN bounding box refinement. target_bbox: [batch, num_rois, (dy, dx, log(dh), log(dw))] target_class_ids: [batch, num_rois].

Loss for Mask R-CNN bounding box refinement. target_bbox: [batch, num_rois, (dy, dx, log(dh), log(dw))] target_class_ids: [batch, num_rois].

Loss for the classifier head of Mask RCNN. target_class_ids: [batch, num_rois]. Integer class IDs. Uses zero padding to fill in the array

Loss for the classifier head of Mask RCNN. target_class_ids: [batch, num_rois]. Integer class IDs. Uses zero padding to fill in the array

Loss for the classifier head of Mask RCNN. target_class_ids: [batch, num_rois]. Integer class IDs. Uses zero padding to fill in the array

Mask binary cross-entropy loss for the masks head. target_masks: [batch, num_rois, height, width]. A float32 tensor of values 0 or 1. Use

Mask binary cross-entropy loss for the masks head. target_masks: [batch, num_rois, height, width]. A float32 tensor of values 0 or 1. Use

Mask binary cross-entropy loss for the masks head. target_masks: [batch, num_rois, height, width]. A float32 tensor of values 0 or 1. Use

Convert predicted output tensors to final detections. Unused. Args: prediction_dict: a dictionary holding prediction tensors. true_im

Refine classified proposals and filter overlaps and return final detections. Inputs: rois: [N, (y1, x1, y2, x2)] in normalized coordi

Refine classified proposals and filter overlaps and return final detections. Inputs: rois: [N, (y1, x1, y2, x2)] in normalized coordi

Refine classified proposals and filter overlaps and return final detections. Inputs: rois: [N, (y1, x1, y2, x2)] in normalized coordi

Build a ResNet graph. architecture: Can be resnet50 or resnet101 stage5: Boolean. If False, stage5 of the network is not created

Build a ResNet graph. architecture: Can be resnet50 or resnet101 stage5: Boolean. If False, stage5 of the network is not created

Returns a map of variables to load from a foreign checkpoint. Args: fine_tune_checkpoint_type: whether to restore from a full detection

Return the RPN bounding box loss graph. config: the model config object. target_bbox: [batch, max positive anchors, (dy, dx, log(dh), log(dw)

Return the RPN bounding box loss graph. config: the model config object. target_bbox: [batch, max positive anchors, (dy, dx, log(dh), log(dw)

Return the RPN bounding box loss graph. config: the model config object. target_bbox: [batch, max positive anchors, (dy, dx, log(dh), log(dw)

RPN anchor classifier loss. rpn_match: [batch, anchors, 1]. Anchor match type. 1=positive, -1=negative, 0=neutral anchor. rpn_

RPN anchor classifier loss. rpn_match: [batch, anchors, 1]. Anchor match type. 1=positive, -1=negative, 0=neutral anchor. rpn_

RPN anchor classifier loss. rpn_match: [batch, anchors, 1]. Anchor match type. 1=positive, -1=negative, 0=neutral anchor. rpn_

Builds the computation graph of Region Proposal Network. feature_map: backbone features [batch, height, width, depth] anchors_per_location: n

Builds the computation graph of Region Proposal Network. feature_map: backbone features [batch, height, width, depth] anchors_per_location: n

Builds the computation graph of Region Proposal Network. feature_map: backbone features [batch, height, width, depth] anchors_per_location: n

Sets model layers as trainable if their names match the given regular expression.

Sets model layers as trainable if their names match the given regular expression.

Sets model layers as trainable if their names match the given regular expression.

Implements Smooth-L1 loss. y_true and y_pred are typicallly: [N, 4], but could be any shape.

Implements Smooth-L1 loss. y_true and y_pred are typically: [N, 4], but could be any shape.

Implements Smooth-L1 loss. y_true and y_pred are typically: [N, 4], but could be any shape.

Override summary() to display summaries of both, the wrapper and inner models.

Override summary() to display summaries of both, the wrapper and inner models.

Train the model.

Train the model.

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

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

Reformats the detections of one image from the format of the neural network output to a format suitable for use in the rest of the app

Redirect loading and saving methods to the inner model. That's where the weights are stored.

Redirect loading and saving methods to the inner model. That's where the weights are stored.

Set values of computed attributes.

anchors: [N, (y1, x1, y2, x2)] anchors defined in image coordinates

Set values of computed attributes.

Class constructor. keras_model: The Keras model to parallelize gpu_count: Number of GPUs. Must be > 1

Set values of computed attributes.

Class constructor. keras_model: The Keras model to parallelize gpu_count: Number of GPUs. Must be > 1

Creates loss function for a DetectionModel. Args: input_queue: BatchQueue object holding enqueued tensor_dicts. create_model_fn: A function

boxes: [num_instance, (y1, x1, y2, x2, class_id)] in image coordinates. masks: [height, width, num_instances] class_ids: [num_instances]

boxes: [num_instance, (y1, x1, y2, x2, class_id)] in image coordinates. masks: [height, width, num_instances] class_ids: [num_instances]

Evaluates tensors in tensor_dict, losses_dict and visualizes examples. This function calls sess.run on tensor_dict, evaluating the original_image

Adds a tf.summary.image for a CDF plot of the values. Normalizes `values` such that they sum to 1, plots the cumulative distribution function and

Finds the ancestor of a TF tensor in the computation graph. tensor: TensorFlow symbolic tensor. name: Name of ancestor tensor to find

Finds the ancestor of a TF tensor in the computation graph. tensor: TensorFlow symbolic tensor. name: Name of ancestor tensor to find