ndarray.image

Image NDArray API of MXNet.

Functions

adjust_lighting([data, alpha, out, name])

Adjust the lighting level of the input.

crop([data, x, y, width, height, out, name])

Crop an image NDArray of shape (H x W x C) or (N x H x W x C) to the given size.

flip_left_right([data, out, name])

Defined in src/operator/image/image_random.cc:L195

flip_top_bottom([data, out, name])

Defined in src/operator/image/image_random.cc:L205

normalize([data, mean, std, out, name])

Normalize an tensor of shape (C x H x W) or (N x C x H x W) with mean and standard deviation.

random_brightness([data, min_factor, …])

Defined in src/operator/image/image_random.cc:L215

random_color_jitter([data, brightness, …])

Defined in src/operator/image/image_random.cc:L246

random_contrast([data, min_factor, …])

Defined in src/operator/image/image_random.cc:L222

random_flip_left_right([data, out, name])

Defined in src/operator/image/image_random.cc:L200

random_flip_top_bottom([data, out, name])

Defined in src/operator/image/image_random.cc:L210

random_hue([data, min_factor, max_factor, …])

Defined in src/operator/image/image_random.cc:L238

random_lighting([data, alpha_std, out, name])

Randomly add PCA noise.

random_saturation([data, min_factor, …])

Defined in src/operator/image/image_random.cc:L230

resize([data, size, keep_ratio, interp, …])

Resize an image NDArray of shape (H x W x C) or (N x H x W x C) to the given size ..

to_tensor([data, out, name])

Converts an image NDArray of shape (H x W x C) or (N x H x W x C)
mxnet.ndarray.image.adjust_lighting(data=None, alpha=_Null, out=None, name=None, **kwargs)

Adjust the lighting level of the input. Follow the AlexNet style.

Defined in src/operator/image/image_random.cc:L254

Parameters

  • data (NDArray) – The input.

  • alpha (tuple of <float>, required) – The lighting alphas for the R, G, B channels.

  • out (NDArray, optional) – The output NDArray to hold the result.

Returns

out – The output of this function.

Return type

NDArray or list of NDArrays

mxnet.ndarray.image.crop(data=None, x=_Null, y=_Null, width=_Null, height=_Null, out=None, name=None, **kwargs)

Crop an image NDArray of shape (H x W x C) or (N x H x W x C) to the given size. .. rubric:: Example

Defined in src/operator/image/crop.cc:L66

Parameters

  • data (NDArray) – The input.

  • x (int, required) – Left boundary of the cropping area.

  • y (int, required) – Top boundary of the cropping area.

  • width (int, required) – Width of the cropping area.

  • height (int, required) – Height of the cropping area.

  • out (NDArray, optional) – The output NDArray to hold the result.

Returns

out – The output of this function.

Return type

NDArray or list of NDArrays

mxnet.ndarray.image.flip_left_right(data=None, out=None, name=None, **kwargs)

Defined in src/operator/image/image_random.cc:L195

Parameters

  • data (NDArray) – The input.

  • out (NDArray, optional) – The output NDArray to hold the result.

Returns

out – The output of this function.

Return type

NDArray or list of NDArrays

mxnet.ndarray.image.flip_top_bottom(data=None, out=None, name=None, **kwargs)

Defined in src/operator/image/image_random.cc:L205

Parameters

  • data (NDArray) – The input.

  • out (NDArray, optional) – The output NDArray to hold the result.

Returns

out – The output of this function.

Return type

NDArray or list of NDArrays

mxnet.ndarray.image.normalize(data=None, mean=_Null, std=_Null, out=None, name=None, **kwargs)
Normalize an tensor of shape (C x H x W) or (N x C x H x W) with mean and

standard deviation.

Given mean (m1, …, mn) and std (s:sub:`1, …, sn)` for n channels, this transform normalizes each channel of the input tensor with:

\[ \begin{align}\begin{aligned} output[i] = (input[i] - m\ :sub:`i`\ ) / s\ :sub:`i`\\If mean or std is scalar, the same value will be applied to all channels.\\Default value for mean is 0.0 and stand deviation is 1.0.\end{aligned}\end{align} \]

Example

Defined in src/operator/image/image_random.cc:L167

Parameters

  • data (NDArray) – Input ndarray

  • mean (tuple of <float>, optional, default=[0,0,0,0]) – Sequence of means for each channel. Default value is 0.

  • std (tuple of <float>, optional, default=[1,1,1,1]) – Sequence of standard deviations for each channel. Default value is 1.

  • out (NDArray, optional) – The output NDArray to hold the result.

Returns

out – The output of this function.

Return type

NDArray or list of NDArrays

mxnet.ndarray.image.random_brightness(data=None, min_factor=_Null, max_factor=_Null, out=None, name=None, **kwargs)

Defined in src/operator/image/image_random.cc:L215

Parameters

  • data (NDArray) – The input.

  • min_factor (float, required) – Minimum factor.

  • max_factor (float, required) – Maximum factor.

  • out (NDArray, optional) – The output NDArray to hold the result.

Returns

out – The output of this function.

Return type

NDArray or list of NDArrays

mxnet.ndarray.image.random_color_jitter(data=None, brightness=_Null, contrast=_Null, saturation=_Null, hue=_Null, out=None, name=None, **kwargs)

Defined in src/operator/image/image_random.cc:L246

Parameters

  • data (NDArray) – The input.

  • brightness (float, required) – How much to jitter brightness.

  • contrast (float, required) – How much to jitter contrast.

  • saturation (float, required) – How much to jitter saturation.

  • hue (float, required) – How much to jitter hue.

  • out (NDArray, optional) – The output NDArray to hold the result.

Returns

out – The output of this function.

Return type

NDArray or list of NDArrays

mxnet.ndarray.image.random_contrast(data=None, min_factor=_Null, max_factor=_Null, out=None, name=None, **kwargs)

Defined in src/operator/image/image_random.cc:L222

Parameters

  • data (NDArray) – The input.

  • min_factor (float, required) – Minimum factor.

  • max_factor (float, required) – Maximum factor.

  • out (NDArray, optional) – The output NDArray to hold the result.

Returns

out – The output of this function.

Return type

NDArray or list of NDArrays

mxnet.ndarray.image.random_flip_left_right(data=None, out=None, name=None, **kwargs)

Defined in src/operator/image/image_random.cc:L200

Parameters

  • data (NDArray) – The input.

  • out (NDArray, optional) – The output NDArray to hold the result.

Returns

out – The output of this function.

Return type

NDArray or list of NDArrays

mxnet.ndarray.image.random_flip_top_bottom(data=None, out=None, name=None, **kwargs)

Defined in src/operator/image/image_random.cc:L210

Parameters

  • data (NDArray) – The input.

  • out (NDArray, optional) – The output NDArray to hold the result.

Returns

out – The output of this function.

Return type

NDArray or list of NDArrays

mxnet.ndarray.image.random_hue(data=None, min_factor=_Null, max_factor=_Null, out=None, name=None, **kwargs)

Defined in src/operator/image/image_random.cc:L238

Parameters

  • data (NDArray) – The input.

  • min_factor (float, required) – Minimum factor.

  • max_factor (float, required) – Maximum factor.

  • out (NDArray, optional) – The output NDArray to hold the result.

Returns

out – The output of this function.

Return type

NDArray or list of NDArrays

mxnet.ndarray.image.random_lighting(data=None, alpha_std=_Null, out=None, name=None, **kwargs)

Randomly add PCA noise. Follow the AlexNet style.

Defined in src/operator/image/image_random.cc:L262

Parameters

  • data (NDArray) – The input.

  • alpha_std (float, optional, default=0.0500000007) – Level of the lighting noise.

  • out (NDArray, optional) – The output NDArray to hold the result.

Returns

out – The output of this function.

Return type

NDArray or list of NDArrays

mxnet.ndarray.image.random_saturation(data=None, min_factor=_Null, max_factor=_Null, out=None, name=None, **kwargs)

Defined in src/operator/image/image_random.cc:L230

Parameters

  • data (NDArray) – The input.

  • min_factor (float, required) – Minimum factor.

  • max_factor (float, required) – Maximum factor.

  • out (NDArray, optional) – The output NDArray to hold the result.

Returns

out – The output of this function.

Return type

NDArray or list of NDArrays

mxnet.ndarray.image.resize(data=None, size=_Null, keep_ratio=_Null, interp=_Null, out=None, name=None, **kwargs)

Resize an image NDArray of shape (H x W x C) or (N x H x W x C) to the given size .. rubric:: Example

Defined in src/operator/image/resize.cc:L71

Parameters

  • data (NDArray) – The input.

  • size (Shape(tuple), optional, default=[]) – Size of new image. Could be (width, height) or (size)

  • keep_ratio (boolean, optional, default=0) – Whether to resize the short edge or both edges to size, if size is give as an integer.

  • interp (int, optional, default='1') – Interpolation method for resizing. By default uses bilinear interpolationOptions are INTER_NEAREST - a nearest-neighbor interpolationINTER_LINEAR - a bilinear interpolationINTER_AREA - resampling using pixel area relationINTER_CUBIC - a bicubic interpolation over 4x4 pixel neighborhoodINTER_LANCZOS4 - a Lanczos interpolation over 8x8 pixel neighborhoodNote that the GPU version only support bilinear interpolation(1) and the result on cpu would be slightly different from gpu.It uses opencv resize function which tend to align center on cpuwhile using contrib.bilinearResize2D which aligns corner on gpu

  • out (NDArray, optional) – The output NDArray to hold the result.

Returns

out – The output of this function.

Return type

NDArray or list of NDArrays

mxnet.ndarray.image.to_tensor(data=None, out=None, name=None, **kwargs)

Converts an image NDArray of shape (H x W x C) or (N x H x W x C) with values in the range [0, 255] to a tensor NDArray of shape (C x H x W) or (N x C x H x W) with values in the range [0, 1]

Example

Defined in src/operator/image/image_random.cc:L92

Parameters

  • data (NDArray) – Input ndarray

  • out (NDArray, optional) – The output NDArray to hold the result.

Returns

out – The output of this function.

Return type

NDArray or list of NDArrays