Computes the gradient of the crop_and_resize op wrt the input image tensor.
tf.raw_ops.CropAndResizeGradImage(
grads,
boxes,
box_ind,
image_size,
T,
method='bilinear',
name=None
)
Args |
|---|
grads
|
A Tensor of type float32.
A 4-D tensor of shape [num_boxes, crop_height, crop_width, depth].
|
boxes
|
A Tensor of type float32.
A 2-D tensor of shape [num_boxes, 4]. The i-th row of the tensor
specifies the coordinates of a box in the box_ind[i] image and is specified
in normalized coordinates [y1, x1, y2, x2]. A normalized coordinate value of
y is mapped to the image coordinate at y * (image_height - 1), so as the
[0, 1] interval of normalized image height is mapped to
[0, image_height - 1] in image height coordinates. We do allow y1 > y2, in
which case the sampled crop is an up-down flipped version of the original
image. The width dimension is treated similarly. Normalized coordinates
outside the[0, 1]range are allowed, in which case we useextrapolation_valueto extrapolate the input image values.
</td>
</tr><tr>
<td>box_ind<a id="box_ind"></a>
</td>
<td>
ATensorof typeint32.
A 1-D tensor of shape[num_boxes]with int32 values in[0, batch).
The value ofbox_ind[i]specifies the image that thei-th box refers to.
</td>
</tr><tr>
<td>image_size<a id="image_size"></a>
</td>
<td>
ATensorof typeint32.
A 1-D tensor with value[batch, image_height, image_width, depth]containing the original image size. Bothimage_heightandimage_widthneed
to be positive.
</td>
</tr><tr>
<td>T<a id="T"></a>
</td>
<td>
A <a href="../../tf/dtypes/DType"><code>tf.DType</code></a> from:tf.float32, tf.half, tf.float64.
</td>
</tr><tr>
<td>method<a id="method"></a>
</td>
<td>
An optionalstringfrom:"bilinear", "nearest". Defaults to"bilinear".
A string specifying the interpolation method. Only 'bilinear' is
supported for now.
</td>
</tr><tr>
<td>name`
|
A name for the operation (optional).
|
Returns |
|---|
A Tensor of type T.
|
