Python functional.resize方法代码示例

# 需要导入模块: from torchvision.transforms import functional [as 别名]
# 或者: from torchvision.transforms.functional import resize [as 别名]
def resize(image, boxes, dims=(300, 300), return_percent_coords=True):
    """
    Resize image. For the SSD300, resize to (300, 300).

    Since percent/fractional coordinates are calculated for the bounding boxes (w.r.t image dimensions) in this process,
    you may choose to retain them.

    :param image: image, a PIL Image
    :param boxes: bounding boxes in boundary coordinates, a tensor of dimensions (n_objects, 4)
    :return: resized image, updated bounding box coordinates (or fractional coordinates, in which case they remain the same)
    """
    # Resize image
    new_image = FT.resize(image, dims)

    # Resize bounding boxes
    old_dims = torch.FloatTensor([image.width, image.height, image.width, image.height]).unsqueeze(0)
    new_boxes = boxes / old_dims  # percent coordinates

    if not return_percent_coords:
        new_dims = torch.FloatTensor([dims[1], dims[0], dims[1], dims[0]]).unsqueeze(0)
        new_boxes = new_boxes * new_dims

    return new_image, new_boxes 

# 需要导入模块: from torchvision.transforms import functional [as 别名]
# 或者: from torchvision.transforms.functional import resize [as 别名]
def _random_crop(self, img_list):
        """Performs random square crop of fixed size.
        Works with list so that all items get the same cropped window (e.g. for buffers).
        """

        w, h = img_list[0].size
        assert w >= self.crop_size and h >= self.crop_size, \
            f'Error: Crop size: {self.crop_size}, Image size: ({w}, {h})'
        cropped_imgs = []
        i = np.random.randint(0, h - self.crop_size + 1)
        j = np.random.randint(0, w - self.crop_size + 1)

        for img in img_list:
            # Resize if dimensions are too small
            if min(w, h) < self.crop_size:
                img = tvF.resize(img, (self.crop_size, self.crop_size))

            # Random crop
            cropped_imgs.append(tvF.crop(img, i, j, self.crop_size, self.crop_size))

        return cropped_imgs 

# 需要导入模块: from torchvision.transforms import functional [as 别名]
# 或者: from torchvision.transforms.functional import resize [as 别名]
def _instance_process(self, img, params):
        if params is None:
            img.img = img.img.resize((self.width, self.height), self.interpolation)

            if img.x is not None:
                img.x = img.x.resize((self.width, self.height), self.interpolation)
            if img.y is not None:
                img.y = img.y.resize((self.width, self.height), self.interpolation)

        else:
            new_width, new_height, x1, y1 = params
            img.img = img.img.resize((new_width, new_height), self.interpolation)
            img.img = img.img.crop((x1, y1, x1 + self.width, y1 + self.height))

            if img.x is not None:
                img.x = img.x.resize((new_width, new_height), self.interpolation)
                img.x = img.x.crop((x1, y1, x1 + self.width, y1 + self.height))

            if img.y is not None:
                img.y = img.y.resize((new_width, new_height), self.interpolation)
                img.y = img.y.crop((x1, y1, x1 + self.width, y1 + self.height))

        return img 

# 需要导入模块: from torchvision.transforms import functional [as 别名]
# 或者: from torchvision.transforms.functional import resize [as 别名]
def __call__(self, img, mask):
        if self.padding > 0:
            img = ImageOps.expand(img, border=self.padding, fill=0)
            mask = ImageOps.expand(mask, border=self.padding, fill=0)

        assert img.size == mask.size
        w, h = img.size
        th, tw = self.size
        if w == tw and h == th:
            return img, mask
        if w < tw or h < th:
            return img.resize((tw, th), Image.BILINEAR), mask.resize(
                (tw, th), Image.NEAREST)

        x1 = random.randint(0, w - tw)
        y1 = random.randint(0, h - th)
        return img.crop((x1, y1, x1 + tw, y1 + th)
                        ), mask.crop((x1, y1, x1 + tw, y1 + th)) 

# 需要导入模块: from torchvision.transforms import functional [as 别名]
# 或者: from torchvision.transforms.functional import resize [as 别名]
def resized_crop(img, i, j, h, w, size, interpolation='BILINEAR'):
    """Crop the given CV Image and resize it to desired size. Notably used in RandomResizedCrop.

    Args:
        img (np.ndarray): Image to be cropped.
        i: Upper pixel coordinate.
        j: Left pixel coordinate.
        h: Height of the cropped image.
        w: Width of the cropped image.
        size (sequence or int): Desired output size. Same semantics as ``scale``.
        interpolation (str, optional): Desired interpolation. Default is
            ``BILINEAR``.
    Returns:
        np.ndarray: Cropped image.
    """
    assert _is_numpy_image(img), 'img should be CV Image'
    img = crop(img, i, j, h, w)
    img = resize(img, size, interpolation)
    return img 

# 需要导入模块: from torchvision.transforms import functional [as 别名]
# 或者: from torchvision.transforms.functional import resize [as 别名]
def cv_transform(img):
    # img = resize(img, size=(100, 300))
    # img = to_tensor(img)
    # img = normalize(img, mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
    # img = pad(img, padding=(10, 10, 20, 20), fill=(255, 255, 255), padding_mode='constant')
    # img = pad(img, padding=(100, 100, 100, 100), fill=5, padding_mode='symmetric')
    # img = crop(img, -40, -20, 1000, 1000)
    # img = center_crop(img, (310, 300))
    # img = resized_crop(img, -10.3, -20, 330, 220, (500, 500))
    # img = hflip(img)
    # img = vflip(img)
    # tl, tr, bl, br, center = five_crop(img, 100)
    # img = adjust_brightness(img, 2.1)
    # img = adjust_contrast(img, 1.5)
    # img = adjust_saturation(img, 2.3)
    # img = adjust_hue(img, 0.5)
    # img = adjust_gamma(img, gamma=3, gain=0.1)
    # img = rotate(img, 10, resample='BILINEAR', expand=True, center=None)
    # img = to_grayscale(img, 3)
    # img = affine(img, 10, (0, 0), 1, 0, resample='BICUBIC', fillcolor=(255,255,0))
    # img = gaussion_noise(img)
    # img = poisson_noise(img)
    img = salt_and_pepper(img)
    return to_tensor(img) 

# 需要导入模块: from torchvision.transforms import functional [as 别名]
# 或者: from torchvision.transforms.functional import resize [as 别名]
def pil_transform(img):
    # img = functional.resize(img, size=(100, 300))
    # img = functional.to_tensor(img)
    # img = functional.normalize(img, mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
    # img = functional.pad(img, padding=(10, 10, 20, 20), fill=(255, 255, 255), padding_mode='constant')
    # img = functional.pad(img, padding=(100, 100, 100, 100), padding_mode='symmetric')
    # img = functional.crop(img, -40, -20, 1000, 1000)
    # img = functional.center_crop(img, (310, 300))
    # img = functional.resized_crop(img, -10.3, -20, 330, 220, (500, 500))
    # img = functional.hflip(img)
    # img = functional.vflip(img)
    # tl, tr, bl, br, center = functional.five_crop(img, 100)
    # img = functional.adjust_brightness(img, 2.1)
    # img = functional.adjust_contrast(img, 1.5)
    # img = functional.adjust_saturation(img, 2.3)
    # img = functional.adjust_hue(img, 0.5)
    # img = functional.adjust_gamma(img, gamma=3, gain=0.1)
    # img = functional.rotate(img, 10, resample=PIL.Image.BILINEAR, expand=True, center=None)
    # img = functional.to_grayscale(img, 3)
    # img = functional.affine(img, 10, (0, 0), 1, 0, resample=PIL.Image.BICUBIC, fillcolor=(255,255,0))

    return functional.to_tensor(img) 

# 需要导入模块: from torchvision.transforms import functional [as 别名]
# 或者: from torchvision.transforms.functional import resize [as 别名]
def __call__(self, img_dict):
        
        if np.random.rand() < self.p:
            data_get_func = img_dict['meta']['get_item_func']
            curr_idx = img_dict['meta']['idx']
            max_idx = img_dict['meta']['max_idx']

            other_idx = np.random.randint(0, max_idx)
            data4augm = data_get_func(other_idx)
            while (curr_idx == other_idx) or (self.same_label and data4augm['label'] != img_dict['label']):
                other_idx = np.random.randint(0, max_idx)
                data4augm = data_get_func(other_idx)

            alpha = np.random.rand()

            keys = ['rgb', 'depth', 'ir']
            for key in keys:
                img_dict[key] = Image.blend(data4augm[key].resize(img_dict[key].size),
                                            img_dict[key],
                                            alpha=alpha)
            if not self.same_label:
                img_dict['label'] = alpha * img_dict['label'] + (1 - alpha) * data4augm['label']
    
        return img_dict 

# 需要导入模块: from torchvision.transforms import functional [as 别名]
# 或者: from torchvision.transforms.functional import resize [as 别名]
def __getitem__(self, index):
        # Apply transforms to the image.
        image = torch.FloatTensor(self.nc,self.out_img_size, self.out_img_size).fill_(-1.)
        # Get the individual images.
        randbox = random.randrange(len(self.metadata['images'][index]))
        imglabel = np.zeros(10, dtype=np.int)
        boxlabel = np.zeros(10, dtype=np.int)
        for i,bb in enumerate(self.metadata['images'][index]):
            imid = random.randrange(self.num_data)
            bbox = [int(bc*self.out_img_size) for bc in bb]
            img, label = self.dataset[imid]
            scImg = FN.resize(img,(bbox[3],bbox[2]))
            image[:, bbox[1]:bbox[1]+bbox[3], bbox[0]:bbox[0]+bbox[2]] = FN.normalize(FN.to_tensor(scImg), mean=(0.5,)*self.nc, std=(0.5,)*self.nc)
            #imglabel[label] = 1
            if i == randbox:
                outBox = FN.normalize(FN.to_tensor(FN.resize(scImg, (self.bbox_out_size, self.bbox_out_size))), mean=(0.5,)*self.nc, std=(0.5,)*self.nc)
                mask = torch.zeros(1,self.out_img_size,self.out_img_size)
                mask[0,bbox[1]:bbox[1]+bbox[3],bbox[0]:bbox[0]+bbox[2]] = 1.
                outbbox = bbox
                #boxlabel[label]=1

        #return image[[0,0,0],::], torch.FloatTensor([1]), outBox[[0,0,0],::], torch.FloatTensor([1]), mask, torch.IntTensor(outbbox)
        return image, torch.FloatTensor([1]), outBox, torch.FloatTensor([1]), mask, torch.IntTensor(outbbox) 

# 需要导入模块: from torchvision.transforms import functional [as 别名]
# 或者: from torchvision.transforms.functional import resize [as 别名]
def __call__(self, image, target):
        size = self.get_size(image.size)
        image = F.resize(image, size)
        target = target.resize(image.size)
        return image, target 

# 需要导入模块: from torchvision.transforms import functional [as 别名]
# 或者: from torchvision.transforms.functional import resize [as 别名]
def __call__(self, image, target):
        if -1 not in self.force_test_scale:
            size = tuple(force_test_scale)
        else:
            size = self.get_size(image.size)
            if self.preprocess_type == "random_crop":
                size = self.reset_size(image.size, size)
        image = F.resize(image, size)
        target = target.resize(image.size)
        return image, target 

# 需要导入模块: from torchvision.transforms import functional [as 别名]
# 或者: from torchvision.transforms.functional import resize [as 别名]
def resize_image(image, desired_width=768, desired_height=384, random_pad=False):
    """Resizes an image keeping the aspect ratio mostly unchanged.

    Returns:
    image: the resized image
    window: (x1, y1, x2, y2). If max_dim is provided, padding might
        be inserted in the returned image. If so, this window is the
        coordinates of the image part of the full image (excluding
        the padding). The x2, y2 pixels are not included.
    scale: The scale factor used to resize the image
    padding: Padding added to the image [left, top, right, bottom]
    """
    # Default window (x1, y1, x2, y2) and default scale == 1.
    w, h = image.size

    width_scale = desired_width / w
    height_scale = desired_height / h
    scale = min(width_scale, height_scale)

    # Resize image using bilinear interpolation
    if scale != 1:
        image = functional.resize(image, (round(h * scale), round(w * scale)))
    w, h = image.size
    y_pad = desired_height - h
    x_pad = desired_width - w
    top_pad = random.randint(0, y_pad) if random_pad else y_pad // 2
    left_pad = random.randint(0, x_pad) if random_pad else x_pad // 2

    padding = (left_pad, top_pad, x_pad - left_pad, y_pad - top_pad)
    assert all([x >= 0 for x in padding])
    image = functional.pad(image, padding)
    window = [left_pad, top_pad, w + left_pad, h + top_pad]

    return image, window, scale, padding 

# 需要导入模块: from torchvision.transforms import functional [as 别名]
# 或者: from torchvision.transforms.functional import resize [as 别名]
def __call__(self, image, target):
        image = F.resize(image, self.resize_shape)
        target = F.resize(
            target, self.resize_shape, interpolation=Image.NEAREST
        )
        return image, target 

# 需要导入模块: from torchvision.transforms import functional [as 别名]
# 或者: from torchvision.transforms.functional import resize [as 别名]
def __call__(self, image, target):
        image = F.resize(image, self.resize_shape)
        return image, target 

# 需要导入模块: from torchvision.transforms import functional [as 别名]
# 或者: from torchvision.transforms.functional import resize [as 别名]
def __call__(self, image, target=None):
        size = self.get_size(image.size)
        image = F.resize(image, size)
        if target is None:
            return image
        target = target.resize(image.size)
        return image, target