Resize loading image
A transformer chain two ImageProcessing together.
adjust the image brightness
Transform byte array(original image file in byte) to OpenCVMat
image channel normalize
random change the channel of an image
Channel normalization with scale factor.
Random adjust brightness, contrast, hue, saturation
expand image, fill the blank part with the meanR, meanG, meanB
a Preprocessing that convert ImageFeature to a Tensor.
Fill part of image with certain pixel value
Crop a fixed area of image
Flip the image horizontally
Adjust image hue
transform opencv mat to tensor
Transform byte array(pixels in byte) to OpenCVMat
Pixel level normalizer, data(i) = data(i) - mean(i)
Random crop a cropWidth
x cropHeight
patch from an image.
Random cropper on uniform distribution with fixed height and width.
Randomly apply the preprocessing to some of the input ImageFeatures, with probability specified.
Randomly apply the preprocessing to some of the input ImageFeatures, with probability specified. E.g. if prob = 0.5, the preprocessing will apply to half of the input ImageFeatures.
Randomly resize an image between minSize and maxSize and scale height and width to each other.
Random sample a bounding box given some constraints and crop the image This is used in SSD training augmentation
horizontally flip the roi
horizontally flip the roi
whether the roi is normalized, i.e. in range [0, 1]
Normalize Roi to [0, 1]
Project gt boxes onto the coordinate system defined by image boundary
Project gt boxes onto the coordinate system defined by image boundary
whether need to meet center constraint, i.e., the center of gt box need be within image boundary
resize the roi according to scale
resize the roi according to scale
whether the roi is normalized, i.e. in range [0, 1]
Adjust image saturation
ImageSet wraps a set of ImageFeature
Transforms tensors that map inputKeys and targetKeys to sample
Normalizes the norm or value range Per image, similar to opencv::normalize https://docs.opencv.org/ref/master/d2/de8/groupcorearray.html #ga87eef7ee3970f86906d69a92cbf064bd ImageNormalize normalizes scale and shift the input features.
Normalizes the norm or value range Per image, similar to opencv::normalize https://docs.opencv.org/ref/master/d2/de8/groupcorearray.html #ga87eef7ee3970f86906d69a92cbf064bd ImageNormalize normalizes scale and shift the input features. Various normalize methods are supported. Eg. NORM_INF, NORM_L1, NORM_L2 or NORM_MINMAX. Pleas notice it's a per image normalization.
a Preprocessing that converts a Spark Row to a BigDL ImageFeature.
Random crop a
cropWidth
xcropHeight
patch from an image. The patch size should be less than the image size.