| 1991af6f5b0fef9a8d10135610a63c1a4df695bf |
|
06-Feb-2017 |
Adam Roberts <adarob@google.com> |
Fixes a couple of mis-formatted error messages.
Change: 146684854
/external/tensorflow/tensorflow/core/kernels/extract_image_patches_op.cc
|
| bc0a56da15eed8738e8a53e2dd340030332df28a |
|
30-Sep-2016 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Cleanup license header
Change: 134714467
/external/tensorflow/tensorflow/core/kernels/extract_image_patches_op.cc
|
| 84f4e8f39e6480294bf27a481ebf17b9ab245a14 |
|
20-Jun-2016 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Refactor Get2dOutputSizes/Get2dOutputSizesVerbose/Get3dOutputSizes to share a common 1-dimensional GetWindowedOutputSize/GetWindowedOutputSizeVerbose.
The output sizes and padding of each dimension of a windowed operation (such as convolution or pooling) are orthogonal and can be computed independently. We can simplify the code by providing a 1D size computation and calling it for each dimension.
Also remove special cases for 1x1 spatial convolutions in dimension calculations; they add complexity and are a case that the general code handles correctly.
In general, 2D convolutions and their gradients have a lot of shape calculation code that is duplicated for each spatial dimension. This CL is a step in the direction of treating spatial dimensions the same so we can share more code.
Change: 125360639
/external/tensorflow/tensorflow/core/kernels/extract_image_patches_op.cc
|
| 6b1b429da364b5f78adc1a3f3360c60dff2c2f41 |
|
03-Jun-2016 |
A. Unique TensorFlower <nobody@tensorflow.org> |
Adds an ExtractImagePatchesOp that performs im2col. Forward only implementation for now. Fixes #2605.
Change: 123983077
/external/tensorflow/tensorflow/core/kernels/extract_image_patches_op.cc
|