Translate image(s) by the passed vectors(s). Args: images: A tensor of shape (num_images, num_rows, num_columns, num_channels) (NHWC), (num_rows, num_columns, num_channels) (HWC), or (num_rows, num_columns) (HW). The rank must be statically known (the shape is not `Ten
(images, translations, interpolation="NEAREST", name=None)
| 100 | |
| 101 | |
| 102 | def translate(images, translations, interpolation="NEAREST", name=None): |
| 103 | """Translate image(s) by the passed vectors(s). |
| 104 | |
| 105 | Args: |
| 106 | images: A tensor of shape (num_images, num_rows, num_columns, num_channels) |
| 107 | (NHWC), (num_rows, num_columns, num_channels) (HWC), or |
| 108 | (num_rows, num_columns) (HW). The rank must be statically known (the |
| 109 | shape is not `TensorShape(None)`. |
| 110 | translations: A vector representing [dx, dy] or (if images has rank 4) |
| 111 | a matrix of length num_images, with a [dx, dy] vector for each image in |
| 112 | the batch. |
| 113 | interpolation: Interpolation mode. Supported values: "NEAREST", "BILINEAR". |
| 114 | name: The name of the op. |
| 115 | |
| 116 | Returns: |
| 117 | Image(s) with the same type and shape as `images`, translated by the given |
| 118 | vector(s). Empty space due to the translation will be filled with zeros. |
| 119 | |
| 120 | Raises: |
| 121 | TypeError: If `image` is an invalid type. |
| 122 | """ |
| 123 | with ops.name_scope(name, "translate"): |
| 124 | return transform( |
| 125 | images, |
| 126 | translations_to_projective_transforms(translations), |
| 127 | interpolation=interpolation) |
| 128 | |
| 129 | |
| 130 | def angles_to_projective_transforms(angles, |
nothing calls this directly
no test coverage detected