Python mrcnn.utils.resize_image() Examples

The following are 15 code examples of mrcnn.utils.resize_image(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module mrcnn.utils , or try the search function .
Example #1
Source File: ros_pix2pose.py    From Pix2Pose with MIT License 6 votes vote down vote up 
def get_rcnn_detection(self,image_t):
        image_t_resized, window, scale, padding, crop = utils.resize_image(
                        np.copy(image_t),
                        min_dim=self.config.IMAGE_MIN_DIM,
                        min_scale=self.config.IMAGE_MIN_SCALE,
                        max_dim=self.config.IMAGE_MAX_DIM,
                        mode=self.config.IMAGE_RESIZE_MODE)
        if(scale!=1):
            print("Warning.. have to adjust the scale")        
        results = self.detection_model.detect([image_t_resized], verbose=0)
        r = results[0]
        rois = r['rois']
        rois = rois - [window[0],window[1],window[0],window[1]]
        obj_orders = np.array(r['class_ids'])-1
        obj_ids=[]
        for obj_order in obj_orders:
            obj_ids.append(self.detection_labels[obj_order])
        #now c_ids are the same annotation those of the names of ply/gt files
        scores = np.array(r['scores'])
        masks = r['masks'][window[0]:window[2],window[1]:window[3],:]
        return rois,obj_orders,obj_ids,scores,masks
Example #2
Source File: 5_evaluation_bop_icp3d.py    From Pix2Pose with MIT License 6 votes vote down vote up 
def get_rcnn_detection(image_t,model):
        image_t_resized, window, scale, padding, crop = utils.resize_image(
                        np.copy(image_t),
                        min_dim=config.IMAGE_MIN_DIM,
                        min_scale=config.IMAGE_MIN_SCALE,
                        max_dim=config.IMAGE_MAX_DIM,
                        mode=config.IMAGE_RESIZE_MODE)
        if(scale!=1):
            print("Warning.. have to adjust the scale")        
        results = model.detect([image_t_resized], verbose=0)
        r = results[0]
        rois = r['rois']
        rois = rois - [window[0],window[1],window[0],window[1]]
        obj_orders = np.array(r['class_ids'])-1
        obj_ids = model_ids[obj_orders] 
        #now c_ids are the same annotation those of the names of ply/gt files
        scores = np.array(r['scores'])
        masks = r['masks'][window[0]:window[2],window[1]:window[3],:]
        return rois,obj_orders,obj_ids,scores,masks
Example #3
Source File: model.py    From dataiku-contrib with Apache License 2.0 5 votes vote down vote up 
def mold_inputs(self, images):
        """Takes a list of images and modifies them to the format expected
        as an input to the neural network.
        images: List of image matrices [height,width,depth]. Images can have
            different sizes.
        Returns 3 Numpy matrices:
        molded_images: [N, h, w, 3]. Images resized and normalized.
        image_metas: [N, length of meta data]. Details about each image.
        windows: [N, (y1, x1, y2, x2)]. The portion of the image that has the
            original image (padding excluded).
        """
        molded_images = []
        image_metas = []
        windows = []
        for image in images:
            # Resize image
            # TODO: move resizing to mold_image()
            molded_image, window, scale, padding, crop = utils.resize_image(
                image,
                min_dim=self.config.IMAGE_MIN_DIM,
                min_scale=self.config.IMAGE_MIN_SCALE,
                max_dim=self.config.IMAGE_MAX_DIM,
                mode=self.config.IMAGE_RESIZE_MODE)
            molded_image = mold_image(molded_image, self.config)
            # Build image_meta
            image_meta = compose_image_meta(
                0, image.shape, molded_image.shape, window, scale,
                np.zeros([self.config.NUM_CLASSES], dtype=np.int32))
            # Append
            molded_images.append(molded_image)
            windows.append(window)
            image_metas.append(image_meta)
        # Pack into arrays
        molded_images = np.stack(molded_images)
        image_metas = np.stack(image_metas)
        windows = np.stack(windows)
        return molded_images, image_metas, windows
Example #4
Source File: 5_evaluation_bop_basic.py    From Pix2Pose with MIT License 5 votes vote down vote up 
def get_rcnn_detection(image_t,model):
        image_t_resized, window, scale, padding, crop = utils.resize_image(
                        np.copy(image_t),
                        min_dim=config.IMAGE_MIN_DIM,
                        min_scale=config.IMAGE_MIN_SCALE,
                        max_dim=config.IMAGE_MAX_DIM,
                        mode=config.IMAGE_RESIZE_MODE)
        if(scale!=1):
            print("Warning.. have to adjust the scale")        
        results = model.detect([image_t_resized], verbose=0)
        r = results[0]
        rois = r['rois']
        if(scale!=1):
            masks_all = r['masks'][window[0]:window[2],window[1]:window[3],:]
            masks = np.zeros((image_t.shape[0],image_t.shape[1],masks_all.shape[2]),bool)
            for mask_id in range(masks_all.shape[2]):
                masks[:,:,mask_id]=resize(masks_all[:,:,mask_id].astype(np.float),(image_t.shape[0],image_t.shape[1]))>0.5
            #resize all the masks            
            rois=rois/scale
            window = np.array(window)
            window[0] = window[0]/scale
            window[1] = window[1]/scale
            window[2] = window[2]/scale
            window[3] = window[3]/scale     
        else:
            masks = r['masks'][window[0]:window[2],window[1]:window[3],:]

        rois = rois - [window[0],window[1],window[0],window[1]]
        obj_orders = np.array(r['class_ids'])-1
        obj_ids = model_ids[obj_orders] 
        #now c_ids are the same annotation those of the names of ply/gt files
        scores = np.array(r['scores'])        
        return rois,obj_orders,obj_ids,scores,masks
Example #5
Source File: 5_evaluation_bop_basic.py    From Pix2Pose with MIT License 5 votes vote down vote up 
def get_retinanet_detection(image_t,model):
        image = preprocess_image(image_t[:,:,::-1]) #needs bgr order bgr?
        image, scale = resize_image(image)
        boxes, scores, labels = model.predict_on_batch(np.expand_dims(image, axis=0))
        boxes /= scale
        boxes = boxes[0]
        scores = scores[0]
        labels = labels[0]
        
        score_mask = scores>0
        if(np.sum(score_mask)==0):
            return np.array([[-1,-1,-1,-1]]),-1,-1,-1

        else:            
            scores = scores[score_mask]
            boxes =  boxes[score_mask]
            labels =  labels[score_mask]
            
            rois = np.zeros((boxes.shape[0],4),np.int)
            rois[:,0] = boxes[:,1]
            rois[:,1] = boxes[:,0]
            rois[:,2] = boxes[:,3]
            rois[:,3] = boxes[:,2]
            obj_orders = labels 
            obj_ids = model_ids[obj_orders]            

            return rois,obj_orders,obj_ids,scores
Example #6
Source File: 5_evaluation_bop_icp3d.py    From Pix2Pose with MIT License 5 votes vote down vote up 
def get_retinanet_detection(image_t,model):
        image = preprocess_image(image_t[:,:,::-1]) #needs bgr order bgr?
        image, scale = resize_image(image)
        boxes, scores, labels = model.predict_on_batch(np.expand_dims(image, axis=0))
        boxes /= scale
        boxes = boxes[0]
        scores = scores[0]
        labels = labels[0]
        
        score_mask = scores>0
        if(np.sum(score_mask)==0):
            return np.array([[-1,-1,-1,-1]]),-1,-1,-1

        else:            
            scores = scores[score_mask]
            boxes =  boxes[score_mask]
            labels =  labels[score_mask]
            
            rois = np.zeros((boxes.shape[0],4),np.int)
            rois[:,0] = boxes[:,1]
            rois[:,1] = boxes[:,0]
            rois[:,2] = boxes[:,3]
            rois[:,3] = boxes[:,2]
            obj_orders = labels 
            obj_ids = model_ids[obj_orders]            

            return rois,obj_orders,obj_ids,scores
Example #7
Source File: model.py    From PanopticSegmentation with MIT License 5 votes vote down vote up 
def mold_inputs(self, images):
        """Takes a list of images and modifies them to the format expected
        as an input to the neural network.
        images: List of image matrices [height,width,depth]. Images can have
            different sizes.

        Returns 3 Numpy matrices:
        molded_images: [N, h, w, 3]. Images resized and normalized.
        image_metas: [N, length of meta data]. Details about each image.
        windows: [N, (y1, x1, y2, x2)]. The portion of the image that has the
            original image (padding excluded).
        """
        molded_images = []
        image_metas = []
        windows = []
        for image in images:
            # Resize image
            # TODO: move resizing to mold_image()
            molded_image, window, scale, padding, crop = utils.resize_image(
                image,
                min_dim=self.config.IMAGE_MIN_DIM,
                min_scale=self.config.IMAGE_MIN_SCALE,
                max_dim=self.config.IMAGE_MAX_DIM,
                mode=self.config.IMAGE_RESIZE_MODE)
            molded_image = mold_image(molded_image, self.config)
            # Build image_meta
            image_meta = compose_image_meta(
                0, image.shape, molded_image.shape, window, scale,
                np.zeros([self.config.NUM_CLASSES], dtype=np.int32))
            # Append
            molded_images.append(molded_image)
            windows.append(window)
            image_metas.append(image_meta)
        # Pack into arrays
        molded_images = np.stack(molded_images)
        image_metas = np.stack(image_metas)
        windows = np.stack(windows)
        return molded_images, image_metas, windows
Example #8
Source File: model.py    From deep-learning-explorer with Apache License 2.0 5 votes vote down vote up 
def mold_inputs(self, images):
        """Takes a list of images and modifies them to the format expected
        as an input to the neural network.
        images: List of image matricies [height,width,depth]. Images can have
            different sizes.

        Returns 3 Numpy matricies:
        molded_images: [N, h, w, 3]. Images resized and normalized.
        image_metas: [N, length of meta data]. Details about each image.
        windows: [N, (y1, x1, y2, x2)]. The portion of the image that has the
            original image (padding excluded).
        """
        molded_images = []
        image_metas = []
        windows = []
        for image in images:
            # Resize image
            # TODO: move resizing to mold_image()
            molded_image, window, scale, padding, crop = utils.resize_image(
                image,
                min_dim=self.config.IMAGE_MIN_DIM,
                min_scale=self.config.IMAGE_MIN_SCALE,
                max_dim=self.config.IMAGE_MAX_DIM,
                mode=self.config.IMAGE_RESIZE_MODE)
            molded_image = mold_image(molded_image, self.config)
            # Build image_meta
            image_meta = compose_image_meta(
                0, image.shape, molded_image.shape, window, scale,
                np.zeros([self.config.NUM_CLASSES], dtype=np.int32))
            # Append
            molded_images.append(molded_image)
            windows.append(window)
            image_metas.append(image_meta)
        # Pack into arrays
        molded_images = np.stack(molded_images)
        image_metas = np.stack(image_metas)
        windows = np.stack(windows)
        return molded_images, image_metas, windows
Example #9
Source File: model.py    From bird_species_classification with MIT License 5 votes vote down vote up 
def mold_inputs(self, images):
        """Takes a list of images and modifies them to the format expected
        as an input to the neural network.
        images: List of image matrices [height,width,depth]. Images can have
            different sizes.

        Returns 3 Numpy matrices:
        molded_images: [N, h, w, 3]. Images resized and normalized.
        image_metas: [N, length of meta data]. Details about each image.
        windows: [N, (y1, x1, y2, x2)]. The portion of the image that has the
            original image (padding excluded).
        """
        molded_images = []
        image_metas = []
        windows = []
        for image in images:
            # Resize image
            # TODO: move resizing to mold_image()
            molded_image, window, scale, padding, crop = utils.resize_image(
                image,
                min_dim=self.config.IMAGE_MIN_DIM,
                min_scale=self.config.IMAGE_MIN_SCALE,
                max_dim=self.config.IMAGE_MAX_DIM,
                mode=self.config.IMAGE_RESIZE_MODE)
            molded_image = mold_image(molded_image, self.config)
            # Build image_meta
            image_meta = compose_image_meta(
                0, image.shape, molded_image.shape, window, scale,
                np.zeros([self.config.NUM_CLASSES], dtype=np.int32))
            # Append
            molded_images.append(molded_image)
            windows.append(window)
            image_metas.append(image_meta)
        # Pack into arrays
        molded_images = np.stack(molded_images)
        image_metas = np.stack(image_metas)
        windows = np.stack(windows)
        return molded_images, image_metas, windows
Example #10
Source File: model_mod_rgb.py    From SpaceNet_Off_Nadir_Solutions with Apache License 2.0 5 votes vote down vote up 
def mold_inputs(self, images):
        """Takes a list of images and modifies them to the format expected
        as an input to the neural network.
        images: List of image matricies [height,width,depth]. Images can have
            different sizes.

        Returns 3 Numpy matricies:
        molded_images: [N, h, w, 3]. Images resized and normalized.
        image_metas: [N, length of meta data]. Details about each image.
        windows: [N, (y1, x1, y2, x2)]. The portion of the image that has the
            original image (padding excluded).
        """
        molded_images = []
        image_metas = []
        windows = []
        for image in images:
            # Resize image
            # TODO: move resizing to mold_image()
            molded_image, window, scale, padding, crop = utils.resize_image(
                image,
                min_dim=self.config.IMAGE_MIN_DIM,
                min_scale=self.config.IMAGE_MIN_SCALE,
                max_dim=self.config.IMAGE_MAX_DIM,
                mode=self.config.IMAGE_RESIZE_MODE)
            molded_image = mold_image(molded_image, self.config)
            # Build image_meta
            image_meta = compose_image_meta(
                0, image.shape, molded_image.shape, window, scale,
                np.zeros([self.config.NUM_CLASSES], dtype=np.int32))
            # Append
            molded_images.append(molded_image)
            windows.append(window)
            image_metas.append(image_meta)
        # Pack into arrays
        molded_images = np.stack(molded_images)
        image_metas = np.stack(image_metas)
        windows = np.stack(windows)
        return molded_images, image_metas, windows
Example #11
Source File: model_mod_mpan.py    From SpaceNet_Off_Nadir_Solutions with Apache License 2.0 5 votes vote down vote up 
def mold_inputs(self, images):
        """Takes a list of images and modifies them to the format expected
        as an input to the neural network.
        images: List of image matricies [height,width,depth]. Images can have
            different sizes.

        Returns 3 Numpy matricies:
        molded_images: [N, h, w, 3]. Images resized and normalized.
        image_metas: [N, length of meta data]. Details about each image.
        windows: [N, (y1, x1, y2, x2)]. The portion of the image that has the
            original image (padding excluded).
        """
        molded_images = []
        image_metas = []
        windows = []
        for image in images:
            # Resize image
            # TODO: move resizing to mold_image()
            molded_image, window, scale, padding, crop = utils.resize_image(
                image,
                min_dim=self.config.IMAGE_MIN_DIM,
                min_scale=self.config.IMAGE_MIN_SCALE,
                max_dim=self.config.IMAGE_MAX_DIM,
                mode=self.config.IMAGE_RESIZE_MODE)
            molded_image = mold_image(molded_image, self.config)
            # Build image_meta
            image_meta = compose_image_meta(
                0, image.shape, molded_image.shape, window, scale,
                np.zeros([self.config.NUM_CLASSES], dtype=np.int32))
            # Append
            molded_images.append(molded_image)
            windows.append(window)
            image_metas.append(image_meta)
        # Pack into arrays
        molded_images = np.stack(molded_images)
        image_metas = np.stack(image_metas)
        windows = np.stack(windows)
        return molded_images, image_metas, windows
Example #12
Source File: model.py    From SpaceNet_Off_Nadir_Solutions with Apache License 2.0 5 votes vote down vote up 
def mold_inputs(self, images):
        """Takes a list of images and modifies them to the format expected
        as an input to the neural network.
        images: List of image matricies [height,width,depth]. Images can have
            different sizes.

        Returns 3 Numpy matricies:
        molded_images: [N, h, w, 3]. Images resized and normalized.
        image_metas: [N, length of meta data]. Details about each image.
        windows: [N, (y1, x1, y2, x2)]. The portion of the image that has the
            original image (padding excluded).
        """
        molded_images = []
        image_metas = []
        windows = []
        for image in images:
            # Resize image
            # TODO: move resizing to mold_image()
            molded_image, window, scale, padding, crop = utils.resize_image(
                image,
                min_dim=self.config.IMAGE_MIN_DIM,
                min_scale=self.config.IMAGE_MIN_SCALE,
                max_dim=self.config.IMAGE_MAX_DIM,
                mode=self.config.IMAGE_RESIZE_MODE)
            molded_image = mold_image(molded_image, self.config)
            # Build image_meta
            image_meta = compose_image_meta(
                0, image.shape, molded_image.shape, window, scale,
                np.zeros([self.config.NUM_CLASSES], dtype=np.int32))
            # Append
            molded_images.append(molded_image)
            windows.append(window)
            image_metas.append(image_meta)
        # Pack into arrays
        molded_images = np.stack(molded_images)
        image_metas = np.stack(image_metas)
        windows = np.stack(windows)
        return molded_images, image_metas, windows
Example #13
Source File: model.py    From deepdiy with MIT License 5 votes vote down vote up 
def mold_inputs(self, images):
        """Takes a list of images and modifies them to the format expected
        as an input to the neural network.
        images: List of image matrices [height,width,depth]. Images can have
            different sizes.

        Returns 3 Numpy matrices:
        molded_images: [N, h, w, 3]. Images resized and normalized.
        image_metas: [N, length of meta data]. Details about each image.
        windows: [N, (y1, x1, y2, x2)]. The portion of the image that has the
            original image (padding excluded).
        """
        molded_images = []
        image_metas = []
        windows = []
        for image in images:
            # Resize image
            # TODO: move resizing to mold_image()
            molded_image, window, scale, padding, crop = utils.resize_image(
                image,
                min_dim=self.config.IMAGE_MIN_DIM,
                min_scale=self.config.IMAGE_MIN_SCALE,
                max_dim=self.config.IMAGE_MAX_DIM,
                mode=self.config.IMAGE_RESIZE_MODE)
            molded_image = mold_image(molded_image, self.config)
            # Build image_meta
            image_meta = compose_image_meta(
                0, image.shape, molded_image.shape, window, scale,
                np.zeros([self.config.NUM_CLASSES], dtype=np.int32))
            # Append
            molded_images.append(molded_image)
            windows.append(window)
            image_metas.append(image_meta)
        # Pack into arrays
        molded_images = np.stack(molded_images)
        image_metas = np.stack(image_metas)
        windows = np.stack(windows)
        return molded_images, image_metas, windows
Example #14
Source File: model_inceptionresnet.py    From cvpr-2018-autonomous-driving-autopilot-solution with MIT License 5 votes vote down vote up 
def mold_inputs(self, images):
        """Takes a list of images and modifies them to the format expected
        as an input to the neural network.
        images: List of image matricies [height,width,depth]. Images can have
            different sizes.

        Returns 3 Numpy matricies:
        molded_images: [N, h, w, 3]. Images resized and normalized.
        image_metas: [N, length of meta data]. Details about each image.
        windows: [N, (y1, x1, y2, x2)]. The portion of the image that has the
            original image (padding excluded).
        """
        molded_images = []
        image_metas = []
        windows = []
        for image in images:
            # Resize image
            # TODO: move resizing to mold_image()
            molded_image, window, scale, padding, crop = utils.resize_image(
                image,
                min_dim=self.config.IMAGE_MIN_DIM,
                min_scale=self.config.IMAGE_MIN_SCALE,
                max_dim=self.config.IMAGE_MAX_DIM,
                mode=self.config.IMAGE_RESIZE_MODE)
            molded_image = mold_image(molded_image, self.config)
            # Build image_meta
            image_meta = compose_image_meta(
                0, image.shape, molded_image.shape, window, scale,
                np.zeros([self.config.NUM_CLASSES], dtype=np.int32))
            # Append
            molded_images.append(molded_image)
            windows.append(window)
            image_metas.append(image_meta)
        # Pack into arrays
        molded_images = np.stack(molded_images)
        image_metas = np.stack(image_metas)
        windows = np.stack(windows)
        return molded_images, image_metas, windows
Example #15
Source File: model.py    From cvpr-2018-autonomous-driving-autopilot-solution with MIT License 5 votes vote down vote up 
def mold_inputs(self, images):
        """Takes a list of images and modifies them to the format expected
        as an input to the neural network.
        images: List of image matricies [height,width,depth]. Images can have
            different sizes.

        Returns 3 Numpy matricies:
        molded_images: [N, h, w, 3]. Images resized and normalized.
        image_metas: [N, length of meta data]. Details about each image.
        windows: [N, (y1, x1, y2, x2)]. The portion of the image that has the
            original image (padding excluded).
        """
        molded_images = []
        image_metas = []
        windows = []
        for image in images:
            # Resize image
            # TODO: move resizing to mold_image()
            molded_image, window, scale, padding, crop = utils.resize_image(
                image,
                min_dim=self.config.IMAGE_MIN_DIM,
                min_scale=self.config.IMAGE_MIN_SCALE,
                max_dim=self.config.IMAGE_MAX_DIM,
                mode=self.config.IMAGE_RESIZE_MODE)
            molded_image = mold_image(molded_image, self.config)
            # Build image_meta
            image_meta = compose_image_meta(
                0, image.shape, molded_image.shape, window, scale,
                np.zeros([self.config.NUM_CLASSES], dtype=np.int32))
            # Append
            molded_images.append(molded_image)
            windows.append(window)
            image_metas.append(image_meta)
        # Pack into arrays
        molded_images = np.stack(molded_images)
        image_metas = np.stack(image_metas)
        windows = np.stack(windows)
        return molded_images, image_metas, windows