MCPcopy Create free account
hub / github.com/dengdan/seglink / preprocess_for_train

Function preprocess_for_train

preprocessing/ssd_vgg_preprocessing.py:234–295  ·  view source on GitHub ↗

Preprocesses the given image for training. Note that the actual resizing scale is sampled from [`resize_size_min`, `resize_size_max`]. Args: image: A `Tensor` representing an image of arbitrary size. output_height: The height of the image after preprocessing.

(image, labels, bboxes, xs, ys,
                         out_shape, data_format='NHWC',
                         scope='ssd_preprocessing_train')

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers 1

preprocess_imageFunction · 0.85

Calls 6

tf_summary_imageFunction · 0.85
distort_colorFunction · 0.85
tf_image_whitenedFunction · 0.85
get_shapeMethod · 0.80

Tested by

no test coverage detected