fastreid.data.transforms.functional Namespace Reference

Functions
	to_tensor (pic)
	int_parameter (level, maxval)
	float_parameter (level, maxval)
	sample_level (n)
	autocontrast (pil_img, *args)
	equalize (pil_img, *args)
	posterize (pil_img, level, *args)
	rotate (pil_img, level, *args)
	solarize (pil_img, level, *args)
	shear_x (pil_img, level, image_size)
	shear_y (pil_img, level, image_size)
	translate_x (pil_img, level, image_size)
	translate_y (pil_img, level, image_size)
	color (pil_img, level, *args)
	contrast (pil_img, level, *args)
	brightness (pil_img, level, *args)
	sharpness (pil_img, level, *args)

Variables
list	augmentations_reid
list	augmentations
list	augmentations_all

Detailed Description

@author:  liaoxingyu
@contact: sherlockliao01@gmail.com

Function Documentation

autocontrast()

fastreid.data.transforms.functional.autocontrast	(		pil_img,
		*	args )

Definition at line 92 of file functional.py.

def autocontrast(pil_img, *args):
    return ImageOps.autocontrast(pil_img)
 
 

brightness()

fastreid.data.transforms.functional.brightness	(		pil_img,
			level,
		*	args )

Definition at line 166 of file functional.py.

def brightness(pil_img, level, *args):
    level = float_parameter(sample_level(level), 1.8) + 0.1
    return ImageEnhance.Brightness(pil_img).enhance(level)
 
 
# operation that overlaps with ImageNet-C's test set

color()

fastreid.data.transforms.functional.color	(		pil_img,
			level,
		*	args )

Definition at line 154 of file functional.py.

def color(pil_img, level, *args):
    level = float_parameter(sample_level(level), 1.8) + 0.1
    return ImageEnhance.Color(pil_img).enhance(level)
 
 
# operation that overlaps with ImageNet-C's test set

contrast()

fastreid.data.transforms.functional.contrast	(		pil_img,
			level,
		*	args )

Definition at line 160 of file functional.py.

def contrast(pil_img, level, *args):
    level = float_parameter(sample_level(level), 1.8) + 0.1
    return ImageEnhance.Contrast(pil_img).enhance(level)
 
 
# operation that overlaps with ImageNet-C's test set

equalize()

fastreid.data.transforms.functional.equalize	(		pil_img,
		*	args )

Definition at line 96 of file functional.py.

def equalize(pil_img, *args):
    return ImageOps.equalize(pil_img)
 
 

float_parameter()

fastreid.data.transforms.functional.float_parameter	(		level,
			maxval )

Helper function to scale `val` between 0 and maxval.
Args:
  level: Level of the operation that will be between [0, `PARAMETER_MAX`].
  maxval: Maximum value that the operation can have. This will be scaled to
    level/PARAMETER_MAX.
Returns:
  A float that results from scaling `maxval` according to `level`.

Definition at line 76 of file functional.py.

def float_parameter(level, maxval):
    """Helper function to scale `val` between 0 and maxval.
    Args:
      level: Level of the operation that will be between [0, `PARAMETER_MAX`].
      maxval: Maximum value that the operation can have. This will be scaled to
        level/PARAMETER_MAX.
    Returns:
      A float that results from scaling `maxval` according to `level`.
    """
    return float(level) * maxval / 10.
 
 

int_parameter()

fastreid.data.transforms.functional.int_parameter	(		level,
			maxval )

Helper function to scale `val` between 0 and maxval .
Args:
  level: Level of the operation that will be between [0, `PARAMETER_MAX`].
  maxval: Maximum value that the operation can have. This will be scaled to
    level/PARAMETER_MAX.
Returns:
  An int that results from scaling `maxval` according to `level`.

Definition at line 64 of file functional.py.

def int_parameter(level, maxval):
    """Helper function to scale `val` between 0 and maxval .
    Args:
      level: Level of the operation that will be between [0, `PARAMETER_MAX`].
      maxval: Maximum value that the operation can have. This will be scaled to
        level/PARAMETER_MAX.
    Returns:
      An int that results from scaling `maxval` according to `level`.
    """
    return int(level * maxval / 10)
 
 

posterize()

fastreid.data.transforms.functional.posterize	(		pil_img,
			level,
		*	args )

Definition at line 100 of file functional.py.

def posterize(pil_img, level, *args):
    level = int_parameter(sample_level(level), 4)
    return ImageOps.posterize(pil_img, 4 - level)
 
 

rotate()

fastreid.data.transforms.functional.rotate	(		pil_img,
			level,
		*	args )

Definition at line 105 of file functional.py.

def rotate(pil_img, level, *args):
    degrees = int_parameter(sample_level(level), 30)
    if np.random.uniform() > 0.5:
        degrees = -degrees
    return pil_img.rotate(degrees, resample=Image.BILINEAR)
 
 

sample_level()

fastreid.data.transforms.functional.sample_level

(

n

)

Definition at line 88 of file functional.py.

def sample_level(n):
    return np.random.uniform(low=0.1, high=n)
 
 

sharpness()

fastreid.data.transforms.functional.sharpness	(		pil_img,
			level,
		*	args )

Definition at line 172 of file functional.py.

def sharpness(pil_img, level, *args):
    level = float_parameter(sample_level(level), 1.8) + 0.1
    return ImageEnhance.Sharpness(pil_img).enhance(level)
 
 

shear_x()

fastreid.data.transforms.functional.shear_x	(		pil_img,
			level,
			image_size )

Definition at line 117 of file functional.py.

def shear_x(pil_img, level, image_size):
    level = float_parameter(sample_level(level), 0.3)
    if np.random.uniform() > 0.5:
        level = -level
    return pil_img.transform(image_size,
                             Image.AFFINE, (1, level, 0, 0, 1, 0),
                             resample=Image.BILINEAR)
 
 

shear_y()

fastreid.data.transforms.functional.shear_y	(		pil_img,
			level,
			image_size )

Definition at line 126 of file functional.py.

def shear_y(pil_img, level, image_size):
    level = float_parameter(sample_level(level), 0.3)
    if np.random.uniform() > 0.5:
        level = -level
    return pil_img.transform(image_size,
                             Image.AFFINE, (1, 0, 0, level, 1, 0),
                             resample=Image.BILINEAR)
 
 

solarize()

fastreid.data.transforms.functional.solarize	(		pil_img,
			level,
		*	args )

Definition at line 112 of file functional.py.

def solarize(pil_img, level, *args):
    level = int_parameter(sample_level(level), 256)
    return ImageOps.solarize(pil_img, 256 - level)
 
 

to_tensor()

fastreid.data.transforms.functional.to_tensor

(

pic

)

Convert a ``PIL Image`` or ``numpy.ndarray`` to tensor.

See ``ToTensor`` for more details.

Args:
    pic (PIL Image or numpy.ndarray): Image to be converted to tensor.

Returns:
    Tensor: Converted image.

Definition at line 12 of file functional.py.

def to_tensor(pic):
    """Convert a ``PIL Image`` or ``numpy.ndarray`` to tensor.
 
    See ``ToTensor`` for more details.
 
    Args:
        pic (PIL Image or numpy.ndarray): Image to be converted to tensor.
 
    Returns:
        Tensor: Converted image.
    """
    if isinstance(pic, np.ndarray):
        assert len(pic.shape) in (2, 3)
        # handle numpy array
        if pic.ndim == 2:
            pic = pic[:, :, None]
 
        img = torch.from_numpy(pic.transpose((2, 0, 1)))
        # backward compatibility
        if isinstance(img, torch.ByteTensor):
            return img.float()
        else:
            return img
 
    # handle PIL Image
    if pic.mode == 'I':
        img = torch.from_numpy(np.array(pic, np.int32, copy=False))
    elif pic.mode == 'I;16':
        img = torch.from_numpy(np.array(pic, np.int16, copy=False))
    elif pic.mode == 'F':
        img = torch.from_numpy(np.array(pic, np.float32, copy=False))
    elif pic.mode == '1':
        img = 255 * torch.from_numpy(np.array(pic, np.uint8, copy=False))
    else:
        img = torch.ByteTensor(torch.ByteStorage.from_buffer(pic.tobytes()))
    # PIL image mode: L, LA, P, I, F, RGB, YCbCr, RGBA, CMYK
    if pic.mode == 'YCbCr':
        nchannel = 3
    elif pic.mode == 'I;16':
        nchannel = 1
    else:
        nchannel = len(pic.mode)
    img = img.view(pic.size[1], pic.size[0], nchannel)
    # put it from HWC to CHW format
    # yikes, this transpose takes 80% of the loading time/CPU
    img = img.transpose(0, 1).transpose(0, 2).contiguous()
    if isinstance(img, torch.ByteTensor):
        return img.float()
    else:
        return img
 
 

translate_x()

fastreid.data.transforms.functional.translate_x	(		pil_img,
			level,
			image_size )

Definition at line 135 of file functional.py.

def translate_x(pil_img, level, image_size):
    level = int_parameter(sample_level(level), image_size[0] / 3)
    if np.random.random() > 0.5:
        level = -level
    return pil_img.transform(image_size,
                             Image.AFFINE, (1, 0, level, 0, 1, 0),
                             resample=Image.BILINEAR)
 
 

translate_y()

fastreid.data.transforms.functional.translate_y	(		pil_img,
			level,
			image_size )

Definition at line 144 of file functional.py.

def translate_y(pil_img, level, image_size):
    level = int_parameter(sample_level(level), image_size[1] / 3)
    if np.random.random() > 0.5:
        level = -level
    return pil_img.transform(image_size,
                             Image.AFFINE, (1, 0, 0, 0, 1, level),
                             resample=Image.BILINEAR)
 
 
# operation that overlaps with ImageNet-C's test set

Variable Documentation

augmentations

list fastreid.data.transforms.functional.augmentations

Initial value:

=  [
    autocontrast, equalize, posterize, rotate, solarize, shear_x, shear_y,
    translate_x, translate_y
]

Definition at line 182 of file functional.py.

augmentations_all

list fastreid.data.transforms.functional.augmentations_all

Initial value:

=  [
    autocontrast, equalize, posterize, rotate, solarize, shear_x, shear_y,
    translate_x, translate_y, color, contrast, brightness, sharpness
]

Definition at line 187 of file functional.py.

augmentations_reid

list fastreid.data.transforms.functional.augmentations_reid

Initial value:

=  [
    autocontrast, equalize, posterize, shear_x, shear_y,
    color, contrast, brightness, sharpness
]

Definition at line 177 of file functional.py.