Python maskrcnn_benchmark.structures.image_list.to_image_list() Examples

def im_detect_bbox_hflip(model, images, target_scale, target_max_size, device):
    """
    Performs bbox detection on the horizontally flipped image.
    Function signature is the same as for im_detect_bbox.
    """
    transform = TT.Compose([
        T.Resize(target_scale, target_max_size),
        TT.RandomHorizontalFlip(1.0),
        TT.ToTensor(),
        T.Normalize(
            mean=cfg.INPUT.PIXEL_MEAN, std=cfg.INPUT.PIXEL_STD, to_bgr255=cfg.INPUT.TO_BGR255
        )
    ])
    images = [transform(image) for image in images]
    images = to_image_list(images, cfg.DATALOADER.SIZE_DIVISIBILITY)
    boxlists = model(images.to(device))

    # Invert the detections computed on the flipped image
    boxlists_inv = [boxlist.transpose(0) for boxlist in boxlists]
    return boxlists_inv 

def im_detect_bbox_hflip(model, images, target_scale, target_max_size, device):
    """
    Performs bbox detection on the horizontally flipped image.
    Function signature is the same as for im_detect_bbox.
    """
    transform = TT.Compose([
        T.Resize(target_scale, target_max_size),
        TT.RandomHorizontalFlip(1.0),
        TT.ToTensor(),
        T.Normalize(
            mean=cfg.INPUT.PIXEL_MEAN, std=cfg.INPUT.PIXEL_STD, to_bgr255=cfg.INPUT.TO_BGR255
        )
    ])
    images = [transform(image) for image in images]
    images = to_image_list(images, cfg.DATALOADER.SIZE_DIVISIBILITY)
    boxlists = model(images.to(device))

    # Invert the detections computed on the flipped image
    boxlists_inv = [boxlist.transpose(0) for boxlist in boxlists]
    return boxlists_inv 

def forward(self, images, targets=None):
        """
        Arguments:
            images (list[Tensor] or ImageList): images to be processed
            targets (list[BoxList]): ground-truth boxes present in the image (optional)
        """
        if self.training and targets is None:
            raise ValueError("In training mode, targets should be passed")
        images = to_image_list(images)
        features = self.backbone(images.tensors)
        proposals, proposal_losses = self.rpn(images, features, targets)
        if self.cfg.MODEL.RPN_ONLY:
            x = features
            result = proposals
            detector_losses = {}
        else:
            x, result, detector_losses = self.roi_heads(features, proposals, targets)

        if self.training:
            losses = {}
            losses.update(detector_losses)
            losses.update(proposal_losses)
            return losses

        return result 

def im_detect_bbox_hflip(model, images, target_scale, target_max_size, device):
    """
    Performs bbox detection on the horizontally flipped image.
    Function signature is the same as for im_detect_bbox.
    """
    transform = TT.Compose([
        T.Resize(target_scale, target_max_size),
        TT.RandomHorizontalFlip(1.0),
        TT.ToTensor(),
        T.Normalize(
            mean=cfg.INPUT.PIXEL_MEAN, std=cfg.INPUT.PIXEL_STD, to_bgr255=cfg.INPUT.TO_BGR255
        )
    ])
    images = [transform(image) for image in images]
    images = to_image_list(images, cfg.DATALOADER.SIZE_DIVISIBILITY)
    boxlists = model(images.to(device))

    # Invert the detections computed on the flipped image
    boxlists_inv = [boxlist.transpose(0) for boxlist in boxlists]
    return boxlists_inv 

def im_detect_bbox_hflip(model, images, target_scale, target_max_size, device):
    """
    Performs bbox detection on the horizontally flipped image.
    Function signature is the same as for im_detect_bbox.
    """
    transform = TT.Compose([
        T.Resize(target_scale, target_max_size),
        TT.RandomHorizontalFlip(1.0),
        TT.ToTensor(),
        T.Normalize(
            mean=cfg.INPUT.PIXEL_MEAN, std=cfg.INPUT.PIXEL_STD, to_bgr255=cfg.INPUT.TO_BGR255
        )
    ])
    images = [transform(image) for image in images]
    images = to_image_list(images, cfg.DATALOADER.SIZE_DIVISIBILITY)
    boxlists = model(images.to(device))

    # Invert the detections computed on the flipped image
    boxlists_inv = [boxlist.transpose(0) for boxlist in boxlists]
    return boxlists_inv 

def forward(self, images, targets=None, features=None):
        """
        Arguments:
            images (list[Tensor] or ImageList): images to be processed
            targets (list[BoxList]): ground-truth boxes present in the image (optional)
            features (list[Tensor]): encoder output features (optional)

        Returns:
            result (list[BoxList] or dict[Tensor]): the output from the model.
                During training, it returns a dict[Tensor] which contains the losses.
                During testing, it returns list[BoxList] contains additional fields
                like `scores`, `labels` and `mask` (for Mask R-CNN models).

        """
        if self.training and targets is None:
            raise ValueError("In training mode, targets should be passed")
        if features is None:
            images = to_image_list(images)
            features = self.encoder(images.tensors)
        return self.decoder(images, features, targets) 

def forward(self, images, targets=None):
        """
        Arguments:
            images (list[Tensor] or ImageList): images to be processed
            targets (list[BoxList]): ground-truth boxes present in the image (optional)

        Returns:
            result (list[BoxList] or dict[Tensor]): the output from the model.
                During training, it returns a dict[Tensor] which contains the losses.
                During testing, it returns list[BoxList] contains additional fields
                like `scores`, `labels` and `mask` (for Mask R-CNN models).

        """
        if self.training and targets is None:
            raise ValueError("In training mode, targets should be passed")
        images = to_image_list(images)
        features = self.backbone(images.tensors)
        proposals, proposal_losses = self.rpn(images, features, targets)
        if self.roi_heads:
            x, result, detector_losses = self.roi_heads(features, proposals, targets)
        else:
            # RPN-only models don't have roi_heads
            x = features
            result = proposals
            detector_losses = {}

        if self.training:
            losses = {}
            losses.update(detector_losses)
            losses.update(proposal_losses)
            return losses

        return result 

def forward(self, images, targets=None):
        """
        Arguments:
            images (list[Tensor] or ImageList): images to be processed
            targets (list[BoxList]): ground-truth boxes present in the image (optional)

        Returns:
            result (list[BoxList] or dict[Tensor]): the output from the model.
                During training, it returns a dict[Tensor] which contains the losses.
                During testing, it returns list[BoxList] contains additional fields
                like `scores`, `labels` and `mask` (for Mask R-CNN models).

        """
        if self.training and targets is None:
            raise ValueError("In training mode, targets should be passed")
        images = to_image_list(images)
        features = self.backbone(images.tensors)
        proposals, proposal_losses = self.rpn(images, features, targets)
        if self.roi_heads:
            x, result, detector_losses = self.roi_heads(features, proposals, targets)
        else:
            # RPN-only models don't have roi_heads
            x = features
            result = proposals
            detector_losses = {}

        if self.training:
            losses = {}
            losses.update(detector_losses)
            losses.update(proposal_losses)
            return losses

        return result 

def compute_prediction(self, original_image):
        """
        Arguments:
            original_image (np.ndarray): an image as returned by OpenCV

        Returns:
            prediction (BoxList): the detected objects. Additional information
                of the detection properties can be found in the fields of
                the BoxList via `prediction.fields()`
        """
        # apply pre-processing to image
        image = self.transforms(original_image)
        # convert to an ImageList, padded so that it is divisible by
        # cfg.DATALOADER.SIZE_DIVISIBILITY
        image_list = to_image_list(image, self.cfg.DATALOADER.SIZE_DIVISIBILITY)
        image_list = image_list.to(self.device)
        # compute predictions
        with torch.no_grad():
            predictions = self.model(image_list)
        predictions = [o.to(self.cpu_device) for o in predictions]

        # always single image is passed at a time
        prediction = predictions[0]

        # reshape prediction (a BoxList) into the original image size
        height, width = original_image.shape[:-1]
        prediction = prediction.resize((width, height))

        if prediction.has_field("mask"):
            # if we have masks, paste the masks in the right position
            # in the image, as defined by the bounding boxes
            masks = prediction.get_field("mask")
            masks = self.masker(masks, prediction)
            prediction.add_field("mask", masks)
        return prediction 

def forward(self, images, targets=None):
        """
        Arguments:
            images (list[Tensor] or ImageList): images to be processed
            targets (list[BoxList]): ground-truth boxes present in the image (optional)

        Returns:
            result (list[BoxList] or dict[Tensor]): the output from the model.
                During training, it returns a dict[Tensor] which contains the losses.
                During testing, it returns list[BoxList] contains additional fields
                like `scores`, `labels` and `mask` (for Mask R-CNN models).

        """
        if self.training and targets is None:
            raise ValueError("In training mode, targets should be passed")
        images = to_image_list(images)
        features = self.backbone(images.tensors)

        if self.fp4p_on:
            # get you C4
            proposals, proposal_losses = self.rpn(images, (features[-1],), targets)
        else:
            proposals, proposal_losses = self.rpn(images, features, targets)

        # features = [feature.detach() for feature in features]

        if self.roi_heads:
            x, result, detector_losses = self.roi_heads(features, proposals, targets)
        else:
            # RPN-only models don't have roi_heads
            x = features
            result = proposals
            detector_losses = {}

        if self.training:
            losses = {}
            losses.update(detector_losses)
            losses.update(proposal_losses)
            return losses

        return result 

def forward(self, images, targets=None):
        """
        Arguments:
            images (list[Tensor] or ImageList): images to be processed
            targets (list[BoxList]): ground-truth boxes present in the image (optional)

        Returns:
            result (list[BoxList] or dict[Tensor]): the output from the model.
                During training, it returns a dict[Tensor] which contains the losses.
                During testing, it returns list[BoxList] contains additional fields
                like `scores`, `labels` and `mask` (for Mask R-CNN models).

        """
        if self.training and targets is None:
            raise ValueError("In training mode, targets should be passed")
        images = to_image_list(images)
        features = self.backbone(images.tensors)
        proposals, proposal_losses = self.rpn(images, features, targets)
        if self.roi_heads:
            x, result, detector_losses = self.roi_heads(features, proposals, targets)
        else:
            # RPN-only models don't have roi_heads
            x = features
            result = proposals
            detector_losses = {}

        if self.training:
            losses = {}
            losses.update(detector_losses)
            losses.update(proposal_losses)
            return losses

        return result 

def __call__(self, batch):
        transposed_batch = list(zip(*batch))
        images = to_image_list(transposed_batch[0], self.size_divisible)
        targets = transposed_batch[1]
        img_ids = transposed_batch[2]
        return images, targets, img_ids 

def create_random_input(cfg, device):
    ret = []
    for x in cfg.INPUT.MIN_SIZE_TRAIN:
        ret.append(torch.rand(3, x, int(x * 1.2)))
    ret = to_image_list(ret, cfg.DATALOADER.SIZE_DIVISIBILITY)
    ret = ret.to(device)
    return ret 

def compute_prediction(self, original_image):
        """
        Arguments:
            original_image (np.ndarray): an image as returned by OpenCV

        Returns:
            prediction (BoxList): the detected objects. Additional information
                of the detection properties can be found in the fields of
                the BoxList via `prediction.fields()`
        """
        # apply pre-processing to image
        image = self.transforms(original_image)
        # convert to an ImageList, padded so that it is divisible by
        # cfg.DATALOADER.SIZE_DIVISIBILITY
        image_list = to_image_list(image, self.cfg.DATALOADER.SIZE_DIVISIBILITY)
        image_list = image_list.to(self.device)
        # compute predictions
        with torch.no_grad():
            predictions = self.model(image_list)
        predictions = [o.to(self.cpu_device) for o in predictions]

        # always single image is passed at a time
        prediction = predictions[0]

        # reshape prediction (a BoxList) into the original image size
        height, width = original_image.shape[:-1]
        prediction = prediction.resize((width, height))

        if prediction.has_field("mask"):
            # if we have masks, paste the masks in the right position
            # in the image, as defined by the bounding boxes
            masks = prediction.get_field("mask")
            # always single image is passed at a time
            masks = self.masker([masks], [prediction])[0]
            prediction.add_field("mask", masks)
        return prediction 

def compute_prediction(self, original_image):
        """
        Arguments:
            original_image (np.ndarray): an image as returned by OpenCV

        Returns:
            prediction (BoxList): the detected objects. Additional information
                of the detection properties can be found in the fields of
                the BoxList via `prediction.fields()`
        """
        # apply pre-processing to image
        image = self.transforms(original_image)
        # convert to an ImageList, padded so that it is divisible by
        # cfg.DATALOADER.SIZE_DIVISIBILITY
        image_list = to_image_list(image, self.cfg.DATALOADER.SIZE_DIVISIBILITY)
        image_list = image_list.to(self.device)
        # compute predictions
        with torch.no_grad():
            predictions = self.model(image_list)
        predictions = [o.to(self.cpu_device) for o in predictions]

        # always single image is passed at a time
        prediction = predictions[0]

        # reshape prediction (a BoxList) into the original image size
        height, width = original_image.shape[:-1]
        prediction = prediction.resize((width, height))

        if prediction.has_field("mask"):
            # if we have masks, paste the masks in the right position
            # in the image, as defined by the bounding boxes
            masks = prediction.get_field("mask")
            # always single image is passed at a time
            masks = self.masker([masks], [prediction])[0]
            prediction.add_field("mask", masks)
        return prediction 

def forward(self, images, targets=None):
        """
        Arguments:
            images (list[Tensor] or ImageList): images to be processed
            targets (list[BoxList]): ground-truth boxes present in the image (optional)

        Returns:
            result (list[BoxList] or dict[Tensor]): the output from the model.
                During training, it returns a dict[Tensor] which contains the losses.
                During testing, it returns list[BoxList] contains additional fields
                like `scores`, `labels` and `mask` (for Mask R-CNN models).

        """
        if self.training and targets is None:
            raise ValueError("In training mode, targets should be passed")
        images = to_image_list(images)
        features = self.backbone(images.tensors)
        proposals, proposal_losses = self.rpn(images, features, targets)
        if self.roi_heads:
            x, result, detector_losses = self.roi_heads(features, proposals, targets)
        else:
            # RPN-only models don't have roi_heads
            x = features
            result = proposals
            detector_losses = {}

        if self.training:
            losses = {}
            losses.update(detector_losses)
            losses.update(proposal_losses)
            return losses

        return result 

def compute_prediction(self, original_image):
        """
        Arguments:
            original_image (np.ndarray): an image as returned by OpenCV

        Returns:
            prediction (BoxList): the detected objects. Additional information
                of the detection properties can be found in the fields of
                the BoxList via `prediction.fields()`
        """
        # apply pre-processing to image
        image = self.transforms(original_image)
        # convert to an ImageList, padded so that it is divisible by
        # cfg.DATALOADER.SIZE_DIVISIBILITY
        image_list = to_image_list(image, self.cfg.DATALOADER.SIZE_DIVISIBILITY)
        image_list = image_list.to(self.device)
        # compute predictions
        with torch.no_grad():
            predictions = self.model(image_list)
        predictions = [o.to(self.cpu_device) for o in predictions]

        # always single image is passed at a time
        prediction = predictions[0]

        # reshape prediction (a BoxList) into the original image size
        height, width = original_image.shape[:-1]
        prediction = prediction.resize((width, height))

        if prediction.has_field("mask"):
            # if we have masks, paste the masks in the right position
            # in the image, as defined by the bounding boxes
            masks = prediction.get_field("mask")
            # always single image is passed at a time
            masks = self.masker([masks], [prediction])[0]
            prediction.add_field("mask", masks)
        return prediction 

def compute_prediction(self, original_image):
        """
        Arguments:
            original_image (np.ndarray): an image as returned by OpenCV

        Returns:
            prediction (BoxList): the detected objects. Additional information
                of the detection properties can be found in the fields of
                the BoxList via `prediction.fields()`
        """
        # apply pre-processing to image
        image = self.transforms(original_image)
        # convert to an ImageList, padded so that it is divisible by
        # cfg.DATALOADER.SIZE_DIVISIBILITY
        image_list = to_image_list(image, self.cfg.DATALOADER.SIZE_DIVISIBILITY)
        image_list = image_list.to(self.device)
        # compute predictions
        with torch.no_grad():
            predictions = self.model(image_list)
        predictions = [o.to(self.cpu_device) for o in predictions]

        # always single image is passed at a time
        prediction = predictions[0]

        # reshape prediction (a BoxList) into the original image size
        height, width = original_image.shape[:-1]
        prediction = prediction.resize((width, height))

        if prediction.has_field("mask"):
            # if we have masks, paste the masks in the right position
            # in the image, as defined by the bounding boxes
            masks = prediction.get_field("mask")
            # always single image is passed at a time
            masks = self.masker([masks], [prediction])[0]
            prediction.add_field("mask", masks)
        return prediction 

def __call__(self, batch):
        transposed_batch = list(zip(*batch))
        images = to_image_list(transposed_batch[0], self.size_divisible)
        targets = transposed_batch[1]
        img_ids = transposed_batch[2]
        return images, targets, img_ids 

def forward(self, images, targets=None):
        """
        Arguments:
            images (list[Tensor] or ImageList): images to be processed
            targets (list[BoxList]): ground-truth boxes present in the image (optional)

        Returns:
            result (list[BoxList] or dict[Tensor]): the output from the model.
                During training, it returns a dict[Tensor] which contains the losses.
                During testing, it returns list[BoxList] contains additional fields
                like `scores`, `labels` and `mask` (for Mask R-CNN models).

        """
        if self.training and targets is None:
            raise ValueError("In training mode, targets should be passed")
        images = to_image_list(images)
        features = self.backbone(images.tensors)
        proposals, proposal_losses = self.rpn(images, features, targets)
        if self.roi_heads:
            x, result, detector_losses = self.roi_heads(features, proposals, targets)
        else:
            # RPN-only models don't have roi_heads
            x = features
            result = proposals
            detector_losses = {}

        if self.training:
            losses = {}
            losses.update(detector_losses)
            losses.update(proposal_losses)
            return losses

        return result 

def compute_prediction(self, original_image):
        """
        Arguments:
            original_image (np.ndarray): an image as returned by OpenCV

        Returns:
            prediction (BoxList): the detected objects. Additional information
                of the detection properties can be found in the fields of
                the BoxList via `prediction.fields()`
        """
        # apply pre-processing to image
        image = self.transforms(original_image)
        # convert to an ImageList, padded so that it is divisible by
        # cfg.DATALOADER.SIZE_DIVISIBILITY
        image_list = to_image_list(image, self.cfg.DATALOADER.SIZE_DIVISIBILITY)
        image_list = image_list.to(self.device)
        # compute predictions
        with torch.no_grad():
            predictions = self.model(image_list)
        predictions = [o.to(self.cpu_device) for o in predictions]

        # always single image is passed at a time
        prediction = predictions[0]

        # reshape prediction (a BoxList) into the original image size
        height, width = original_image.shape[:-1]
        prediction = prediction.resize((width, height))

        if prediction.has_field("mask"):
            # if we have masks, paste the masks in the right position
            # in the image, as defined by the bounding boxes
            masks = prediction.get_field("mask")
            masks = self.masker(masks, prediction)
            prediction.add_field("mask", masks)
        return prediction 

def forward(self, images, targets=None):
        """
        Arguments:
            images (list[Tensor] or ImageList): images to be processed
            targets (list[BoxList]): ground-truth boxes present in the image (optional)

        Returns:
            result (list[BoxList] or dict[Tensor]): the output from the model.
                During training, it returns a dict[Tensor] which contains the losses.
                During testing, it returns list[BoxList] contains additional fields
                like `scores`, `labels` and `mask` (for Mask R-CNN models).

        """
        if self.training and targets is None:
            raise ValueError("In training mode, targets should be passed")
        images = to_image_list(images)
        features = self.backbone(images.tensors)
        proposals, proposal_losses = self.rpn(images, features, targets)
        if self.roi_heads:
            x, result, detector_losses = self.roi_heads(features, proposals, targets)
        else:
            # RPN-only models don't have roi_heads
            x = features
            result = proposals
            detector_losses = {}

        if self.training:
            losses = {}
            losses.update(detector_losses)
            losses.update(proposal_losses)
            return losses

        return result 

def __call__(self, batch):
        transposed_batch = list(zip(*batch))
        images = to_image_list(transposed_batch[0], self.size_divisible)
        targets = transposed_batch[1]
        img_ids = transposed_batch[2]
        return images, targets, img_ids 

def forward(self, images, targets=None):
        """
        Arguments:
            images (list[Tensor] or ImageList): images to be processed
            targets (list[BoxList]): ground-truth boxes present in the image (optional)

        Returns:
            result (list[BoxList] or dict[Tensor]): the output from the model.
                During training, it returns a dict[Tensor] which contains the losses.
                During testing, it returns list[BoxList] contains additional fields
                like `scores`, `labels` and `mask` (for Mask R-CNN models).

        """
        if self.training and targets is None:
            raise ValueError("In training mode, targets should be passed")
        images = to_image_list(images)
        features = self.backbone(images.tensors)

        # Retina RPN Output
        rpn_features = features
        if self.cfg.RETINANET.BACKBONE == "p2p7":
            rpn_features = features[1:]
        (anchors, detections), detector_losses = self.rpn(images, rpn_features, targets)
        if self.training:
            return detector_losses
        else:
            return detections 

def forward(self, images, targets=None):
        """
        Arguments:
            images (list[Tensor] or ImageList): images to be processed
            targets (list[BoxList]): ground-truth boxes present in the image (optional)

        Returns:
            result (list[BoxList] or dict[Tensor]): the output from the model.
                During training, it returns a dict[Tensor] which contains the losses.
                During testing, it returns list[BoxList] contains additional fields
                like `scores`, `labels` and `mask` (for Mask R-CNN models).

        """
        assert self.training is False

        all_anchors, all_box_cls, all_box_regression = [], [], []
        for resizer in self.resizers:
            image_size = images.image_sizes[0]
            size = resizer.get_size(image_size[::-1])
            aug_images = interpolate(
                images.tensors[:, :, :image_size[0], :image_size[1]], size, mode='bilinear', align_corners=True
            )[0]
            aug_images = to_image_list(aug_images, size_divisible=self.retinanet.cfg.DATALOADER.SIZE_DIVISIBILITY)
            features = self.retinanet.backbone(aug_images.tensors)
            if self.retinanet.cfg.RETINANET.BACKBONE == "p2p7":
                features = features[1:]
            box_cls, box_regression = self.retinanet.rpn.head(features)
            anchors = self.retinanet.rpn.anchor_generator(aug_images, features)[0]
            all_anchors.extend(anchors), all_box_cls.extend(box_cls), all_box_regression.extend(box_regression)

        detections = self.retinanet.rpn.box_selector_test([all_anchors], all_box_cls, all_box_regression)

        return detections 

def __call__(self, batch):
        transposed_batch = list(zip(*batch))
        images = to_image_list(transposed_batch[0], self.size_divisible)
        targets = transposed_batch[1]
        img_ids = transposed_batch[2]
        return images, targets, img_ids 

def compute_prediction(self, original_image):
        """
        Arguments:
            original_image (np.ndarray): an image as returned by OpenCV

        Returns:
            prediction (BoxList): the detected objects. Additional information
                of the detection properties can be found in the fields of
                the BoxList via `prediction.fields()`
        """
        # apply pre-processing to image
        image = self.transforms(original_image)
        # convert to an ImageList, padded so that it is divisible by
        # cfg.DATALOADER.SIZE_DIVISIBILITY
        image_list = to_image_list(image, self.cfg.DATALOADER.SIZE_DIVISIBILITY)
        image_list = image_list.to(self.device)
        # compute predictions
        with torch.no_grad():
            predictions = self.model(image_list)
        predictions = [o.to(self.cpu_device) for o in predictions]

        # always single image is passed at a time
        prediction = predictions[0]

        # reshape prediction (a BoxList) into the original image size
        height, width = original_image.shape[:-1]
        prediction = prediction.resize((width, height))

        if prediction.has_field("mask"):
            # if we have masks, paste the masks in the right position
            # in the image, as defined by the bounding boxes
            masks = prediction.get_field("mask")
            # always single image is passed at a time
            masks = self.masker([masks], [prediction])[0]
            prediction.add_field("mask", masks)
        return prediction 

def forward(self, images, targets=None):
        """
        Arguments:
            images (list[Tensor] or ImageList): images to be processed
            targets (list[BoxList]): ground-truth boxes present in the image (optional)

        Returns:
            result (list[BoxList] or dict[Tensor]): the output from the model.
                During training, it returns a dict[Tensor] which contains the losses.
                During testing, it returns list[BoxList] contains additional fields
                like `scores`, `labels` and `mask` (for Mask R-CNN models).

        """
        if self.training and targets is None:
            raise ValueError("In training mode, targets should be passed")
        images = to_image_list(images)
        features = self.backbone(images.tensors)
        proposals, proposal_losses = self.rpn(images, features, targets)
        if self.roi_heads:
            x, result, detector_losses = self.roi_heads(features, proposals, targets)
        else:
            # RPN-only models don't have roi_heads
            x = features
            result = proposals
            detector_losses = {}

        if self.training:
            losses = {}
            losses.update(detector_losses)
            losses.update(proposal_losses)
            return losses

        return result 

def forward(self, images, targets=None):
        """
        Arguments:
            images (list[Tensor] or ImageList): images to be processed
            targets (list[BoxList]): ground-truth boxes present in the image (optional)

        Returns:
            result (list[BoxList] or dict[Tensor]): the output from the model.
                During training, it returns a dict[Tensor] which contains the losses.
                During testing, it returns list[BoxList] contains additional fields
                like `scores`, `labels` and `mask` (for Mask R-CNN models).

        """
        if self.training and targets is None:
            raise ValueError("In training mode, targets should be passed")
        images = to_image_list(images)
        features = self.backbone(images.tensors)

        # ######################## add by hui #############################################
        features = self.sampler(features)        # up sampler or down sampler or do nothing
        # #################################################################################

        proposals, proposal_losses = self.rpn(images, features, targets)
        if self.roi_heads:
            x, result, detector_losses = self.roi_heads(features, proposals, targets)
        else:
            # RPN-only models don't have roi_heads
            x = features
            result = proposals
            detector_losses = {}

        if self.training:
            losses = {}
            losses.update(detector_losses)
            losses.update(proposal_losses)
            return losses

        return result 

def __call__(self, batch):
        transposed_batch = list(zip(*batch))
        images = to_image_list(transposed_batch[0], self.size_divisible)
        targets = transposed_batch[1]
        img_ids = transposed_batch[2]
        return images, targets, img_ids