Python utils.unmold_mask() Examples

def unmold_detections(self, detections, mrcnn_mask, image_shape, window):
        """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
        application.

        detections: [N, (y1, x1, y2, x2, class_id, score)]
        mrcnn_mask: [N, height, width, num_classes]
        image_shape: [height, width, depth] Original size of the image before resizing
        window: [y1, x1, y2, x2] Box in the image where the real image is
                excluding the padding.

        Returns:
        boxes: [N, (y1, x1, y2, x2)] Bounding boxes in pixels
        class_ids: [N] Integer class IDs for each bounding box
        scores: [N] Float probability scores of the class_id
        masks: [height, width, num_instances] Instance masks
        """
        # How many detections do we have?
        # Detections array is padded with zeros. Find the first class_id == 0.
        zero_ix = np.where(detections[:, 4] == 0)[0]
        N = zero_ix[0] if zero_ix.shape[0] > 0 else detections.shape[0]

        # Extract boxes, class_ids, scores, and class-specific masks
        boxes = detections[:N, :4]
        class_ids = detections[:N, 4].astype(np.int32)
        scores = detections[:N, 5]
        masks = mrcnn_mask[np.arange(N), :, :, class_ids]

        # Compute scale and shift to translate coordinates to image domain.
        h_scale = image_shape[0] / (window[2] - window[0])
        w_scale = image_shape[1] / (window[3] - window[1])
        scale = min(h_scale, w_scale)
        shift = window[:2]  # y, x
        scales = np.array([scale, scale, scale, scale])
        shifts = np.array([shift[0], shift[1], shift[0], shift[1]])

        # Translate bounding boxes to image domain
        boxes = np.multiply(boxes - shifts, scales).astype(np.int32)

        # Filter out detections with zero area. Often only happens in early
        # stages of training when the network weights are still a bit random.
        exclude_ix = np.where(
            (boxes[:, 2] - boxes[:, 0]) * (boxes[:, 3] - boxes[:, 1]) <= 0)[0]
        if exclude_ix.shape[0] > 0:
            boxes = np.delete(boxes, exclude_ix, axis=0)
            class_ids = np.delete(class_ids, exclude_ix, axis=0)
            scores = np.delete(scores, exclude_ix, axis=0)
            masks = np.delete(masks, exclude_ix, axis=0)
            N = class_ids.shape[0]

        # Resize masks to original image size and set boundary threshold.
        full_masks = []
        for i in range(N):
            # Convert neural network mask to full size mask
            full_mask = utils.unmold_mask(masks[i], boxes[i], image_shape)
            full_masks.append(full_mask)
        full_masks = np.stack(full_masks, axis=-1)\
            if full_masks else np.empty((0,) + masks.shape[1:3])

        return boxes, class_ids, scores, full_masks 

def unmold_detections(self, detections, mrcnn_mask, image_shape, window):
        """Reformat the detections of one image from the format of the neural
        network output to a format suitable for use in the rest of the application.
        detections: [N, (z1, y1, x1, z2, y2, x2, class_id, score)]
        mrcnn_mask: [N, depth, height, width, num_classes]
        image_shape: [channels, depth, height, width] Original size of the image before resizing
        window: [z1, y1, x1, z2, y2, x2] Box in the image where the real image is excluding the padding.
        Returns:
        boxes: [N, (y1, x1, z1, y2, x2, z2)] Bounding boxes in pixels
        class_ids: [N] Integer class IDs for each bounding box
        scores: [N] Float probability scores of the class_id
        masks: [height, width, depth] normal shape full mask
        """
        start_time = time.time()
        # How many detections do we have?
        # Detections array is padded with zeros. Find the first class_id == 0.
        zero_ix = np.where(detections[:, 6] == 0)[0]
        N = zero_ix[0] if zero_ix.shape[0] > 0 else detections.shape[0]

        # Extract boxes, class_ids, scores, and class-specific masks
        boxes = detections[:N, :6].astype(np.int32)
        class_ids = detections[:N, 6].astype(np.int32)
        scores = detections[:N, 7]
        masks = mrcnn_mask[np.arange(N), :, :, :, :]

        # Compute scale and shift to translate the bounding boxes to image domain.
        d_scale = image_shape[1] / (window[3] - window[0])
        h_scale = image_shape[2] / (window[4] - window[1])
        w_scale = image_shape[3] / (window[5] - window[2])
        shift = window[:3]  # z, y, x
        scales = np.array([d_scale, h_scale, w_scale, d_scale, h_scale, w_scale])
        shifts = np.array([shift[0], shift[1], shift[2], shift[0], shift[1], shift[2]])
        boxes = np.multiply(boxes - shifts, scales).astype(np.int32)

        # Filter out detections with zero area. Often only happens in early
        # stages of training when the network weights are still a bit random.
        exclude_ix = np.where(
            (boxes[:, 3] - boxes[:, 0]) * (boxes[:, 4] - boxes[:, 1]) * (boxes[:, 5] - boxes[:, 2]) <= 0)[0]
        if exclude_ix.shape[0] > 0:
            boxes = np.delete(boxes, exclude_ix, axis=0)
            class_ids = np.delete(class_ids, exclude_ix, axis=0)
            scores = np.delete(scores, exclude_ix, axis=0)
            masks = np.delete(masks, exclude_ix, axis=0)

        # Resize masks to original image size.
        full_masks = utils.unmold_mask(masks[0], boxes[0], image_shape)
        full_mask = np.argmax(full_masks, axis=3)

        # Transform the shapes of boxes to normal shape.
        boxes[:, [0, 1, 2, 3, 4, 5]] = boxes[:, [1, 2, 0, 4, 5, 3]]
        print("unmold done, using time", time.time() - start_time)

        return boxes, np.arange(1, 8), scores, full_mask.transpose((1, 2, 0))


############################################################
#  Data Formatting
############################################################ 

def unmold_detections(self, detections, mrcnn_mask, image_shape, window):
        """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
        application.

        detections: [N, (y1, x1, y2, x2, class_id, score)]
        mrcnn_mask: [N, height, width, num_classes]
        image_shape: [height, width, depth] Original size of the image before resizing
        window: [y1, x1, y2, x2] Box in the image where the real image is
                excluding the padding.

        Returns:
        boxes: [N, (y1, x1, y2, x2)] Bounding boxes in pixels
        class_ids: [N] Integer class IDs for each bounding box
        scores: [N] Float probability scores of the class_id
        masks: [height, width, num_instances] Instance masks
        """
        # How many detections do we have?
        # Detections array is padded with zeros. Find the first class_id == 0.
        zero_ix = np.where(detections[:, 4] == 0)[0]
        N = zero_ix[0] if zero_ix.shape[0] > 0 else detections.shape[0]

        # Extract boxes, class_ids, scores, and class-specific masks
        boxes = detections[:N, :4]
        class_ids = detections[:N, 4].astype(np.int32)
        scores = detections[:N, 5]
        masks = mrcnn_mask[np.arange(N), :, :, class_ids]

        # Compute scale and shift to translate coordinates to image domain.
        h_scale = image_shape[0] / (window[2] - window[0])
        w_scale = image_shape[1] / (window[3] - window[1])
        scale = min(h_scale, w_scale)
        shift = window[:2]  # y, x
        scales = np.array([scale, scale, scale, scale])
        shifts = np.array([shift[0], shift[1], shift[0], shift[1]])

        # Translate bounding boxes to image domain
        boxes = np.multiply(boxes - shifts, scales).astype(np.int32)

        # Filter out detections with zero area. Often only happens in early
        # stages of training when the network weights are still a bit random.
        exclude_ix = np.where(
            (boxes[:, 2] - boxes[:, 0]) * (boxes[:, 3] - boxes[:, 1]) <= 0)[0]
        if exclude_ix.shape[0] > 0:
            boxes = np.delete(boxes, exclude_ix, axis=0)
            class_ids = np.delete(class_ids, exclude_ix, axis=0)
            scores = np.delete(scores, exclude_ix, axis=0)
            masks = np.delete(masks, exclude_ix, axis=0)
            N = class_ids.shape[0]

        # Resize masks to original image size and set boundary threshold.
        full_masks = []
        for i in range(N):
            # Convert neural network mask to full size mask
            full_mask = utils.unmold_mask(masks[i], boxes[i], image_shape)
            full_masks.append(full_mask)
        full_masks = np.stack(full_masks, axis=-1)\
            if full_masks else np.empty((0,) + masks.shape[1:3])

        return boxes, class_ids, scores, full_masks 

def unmold_detections(self, detections, mrcnn_mask, image_shape, window):
        """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
        application.

        detections: [N, (y1, x1, y2, x2, class_id, score)]
        mrcnn_mask: [N, height, width, num_classes]
        image_shape: [height, width, depth] Original size of the image before resizing
        window: [y1, x1, y2, x2] Box in the image where the real image is
                excluding the padding.

        Returns:
        boxes: [N, (y1, x1, y2, x2)] Bounding boxes in pixels
        class_ids: [N] Integer class IDs for each bounding box
        scores: [N] Float probability scores of the class_id
        masks: [height, width, num_instances] Instance masks
        """
        # How many detections do we have?
        # Detections array is padded with zeros. Find the first class_id == 0.
        zero_ix = np.where(detections[:, 4] == 0)[0]
        N = zero_ix[0] if zero_ix.shape[0] > 0 else detections.shape[0]

        # Extract boxes, class_ids, scores, and class-specific masks
        boxes = detections[:N, :4]
        class_ids = detections[:N, 4].astype(np.int32)
        scores = detections[:N, 5]
        masks = mrcnn_mask[np.arange(N), :, :, class_ids]

        # Compute scale and shift to translate coordinates to image domain.
        h_scale = image_shape[0] / (window[2] - window[0])
        w_scale = image_shape[1] / (window[3] - window[1])
        scale = min(h_scale, w_scale)
        shift = window[:2]  # y, x
        scales = np.array([scale, scale, scale, scale])
        shifts = np.array([shift[0], shift[1], shift[0], shift[1]])

        # Translate bounding boxes to image domain
        boxes = np.multiply(boxes - shifts, scales).astype(np.int32)

        # Filter out detections with zero area. Often only happens in early
        # stages of training when the network weights are still a bit random.
        exclude_ix = np.where(
            (boxes[:, 2] - boxes[:, 0]) * (boxes[:, 3] - boxes[:, 1]) <= 0)[0]
        if exclude_ix.shape[0] > 0:
            boxes = np.delete(boxes, exclude_ix, axis=0)
            class_ids = np.delete(class_ids, exclude_ix, axis=0)
            scores = np.delete(scores, exclude_ix, axis=0)
            masks = np.delete(masks, exclude_ix, axis=0)
            N = class_ids.shape[0]

        # Resize masks to original image size and set boundary threshold.
        full_masks = []
        for i in range(N):
            # Convert neural network mask to full size mask
            full_mask = utils.unmold_mask(masks[i], boxes[i], image_shape)
            full_masks.append(full_mask)
        full_masks = np.stack(full_masks, axis=-1)\
            if full_masks else np.empty((0,) + masks.shape[1:3])

        return boxes, class_ids, scores, full_masks