ExtractImagePatches

tensorflow C++ API

tensorflow::ops::ExtractImagePatches

Extract patches from images and put them in the "depth" output dimension.

Summary

Arguments:

• scope: A Scope object
• images: 4-D Tensor with shape [batch, in_rows, in_cols, depth] .
• ksizes: The size of the sliding window for each dimension of images .
• strides: 1-D of length 4. How far the centers of two consecutive patches are in the images. Must be: [1, stride_rows, stride_cols, 1] .
• rates: 1-D of length 4. Must be: [1, rate_rows, rate_cols, 1] . This is the input stride, specifying how far two consecutive patch samples are in the input. Equivalent to extracting patches with patch_sizes_eff = patch_sizes + (patch_sizes - 1) * (rates - 1) , followed by subsampling them spatially by a factor of rates .
• padding: The type of padding algorithm to use.

We specify the size-related attributes as:

```python ksizes = [1, ksize_rows, ksize_cols, 1] strides = [1, strides_rows, strides_cols, 1] rates = [1, rates_rows, rates_cols, 1] ```

Returns:

• Output : 4-D Tensor with shape [batch, out_rows, out_cols, ksize_rows * ksize_cols * depth] containing image patches with size ksize_rows x ksize_cols x depth vectorized in the "depth" dimension.

ExtractImagePatches block

Source link :https://github.com/EXPNUNI/enuSpaceTensorflow/blob/master/enuSpaceTensorflow/tf_array_ops.cpp

Argument:

• Scope scope : A Scope object (A scope is generated automatically each page. A scope is not connected.)
• Input images : A Tensor . Must be one of the following types: float , int32, int64 , uint8 , int16 , int8 , uint16 , half . 4-D Tensor with shape [batch, in_rows, in_cols, depth] .
• gtl::ArraySlice<int> ksizes : A list of ints that has length >= 4 . The size of the sliding window for each dimension of images .
• gtl::ArraySlice<int> strides : A list of ints that has length >= 4 . 1-D of length 4. How far the centers of two consecutive patches are in the images. Must be: [1, stride_rows, stride_cols, 1] .
• gtl::ArraySlice<int> rates : A list of ints that has length >= 4 . 1-D of length 4. Must be: [1, rate_rows, rate_cols, 1] . This is the input stride, specifying how far two consecutive patch samples are in the input. Equivalent to extracting patches with patch_sizes_eff = patch_sizes + (patch_sizes - 1) * (rates - 1) , followed by subsampling them spatially by a factor of rates .
• StringPiece padding: Astringfrom:"SAME", "VALID". The type of padding algorithm to use.

Return:

• Output output : Output object of ExtractImagePatches class object.

Result:

• std::vector(Tensor) result_output : A Tensor . Has the same type as images. 4-D Tensor with shape [batch, out_rows, out_cols, ksize_rows * ksize_cols * depth] containing image patches with size ksize_rows x ksize_cols x depth vectorized in the "depth" dimension.

Using Method