HomeSort by relevance Sort by last modified time
    Searched full:convolution (Results 51 - 75 of 406) sorted by null

1 23 4 5 6 7 8 91011>>

  /external/tensorflow/tensorflow/python/keras/_impl/keras/applications/
mobilenet.py 120 """Depthwise separable 2D convolution.
123 just the first step in a depthwise spatial convolution
130 width and height of the 2D convolution window.
134 specifying the strides of the convolution along the width and height.
140 depth_multiplier: The number of depthwise convolution output channels
142 The total number of depthwise convolution output
349 depth_multiplier: depth multiplier for depthwise convolution
389 'depthwise convolution.')
554 """Adds an initial convolution layer (with batch normalization and relu6).
564 (i.e. the number of output filters in the convolution)
    [all...]
  /external/tensorflow/tensorflow/python/ops/
nn_ops.py 61 This is used to implement the more generic `convolution` function, which
140 raise ValueError("Rank of convolution must be known")
329 filter_shape: If padding = "SAME", specifies the shape of the convolution
447 # Padding required to reduce to "VALID" convolution
606 This is used by `convolution` and `pool`.
646 @tf_export("nn.convolution")
647 def convolution( function
659 or atrous convolution (also known as convolution with holes or dilated
660 convolution, based on the French word "trous" meaning holes in English) vi
    [all...]
  /external/tensorflow/tensorflow/compiler/xla/service/
transpose_folding_test.cc 48 [](const HloInstruction& convolution,
213 // Test that a two dimension swap of the kernel gets folded into convolution.
248 // Instructions after folding: x, y, and the convolution.
266 // Test that a complex transpose of the kernel gets folded into convolution.
301 // Instructions after folding: x, y, and the convolution.
325 // Test that a transpose of the activations gets folded into convolution.
359 // Instructions after folding: x, y, and the convolution.
389 // convolution.
423 // Instructions after folding: x, y, and the convolution.
  /external/tensorflow/tensorflow/python/keras/_impl/keras/layers/
local.py 44 # apply a unshared weight convolution 1d of length 3 to a sequence with
56 (i.e. the number of output filters in the convolution).
58 specifying the length of the 1D convolution window.
60 specifying the stride length of the convolution.
209 # apply a 3x3 unshared weights convolution with 64 output filters on a
218 # add a 3x3 unshared weights convolution on top, with 32 output filters:
225 (i.e. the number of output filters in the convolution).
227 width and height of the 2D convolution window.
231 specifying the strides of the convolution along the width and height.
  /external/tensorflow/tensorflow/python/kernel_tests/
neon_depthwise_conv_op_test.py 32 """Iterator for different convolution shapes, strides and paddings.
36 convolution parameters.
56 """Iterator for different convolution shapes, strides and paddings.
63 convolution parameters.
96 """Verifies the output values of the convolution function.
185 """Verifies the output values of the depthwise convolution function.
  /external/ImageMagick/ImageMagick/api/
morphology.html 59 <p>AcquireKernelInfo() takes the given string (generally supplied by the user) and converts it into a Morphology/Convolution Kernel. This allows users to specify a kernel from a number of pre-defined kernels, or to fully specify their own kernel for a specific Convolution or Morphology Operation.</p>
101 <dd>the Morphology/Convolution kernel wanted. </dd>
132 <dd> Convolution Kernels </dd>
162 <dd> Named Constant Convolution Kernels </dd>
170 <dd> Sobel:{angle} Sobel 'Edge' convolution kernel (3x3) | -1, 0, 1 | | -2, 0,-2 | | -1, 0, 1 | </dd>
172 <dd> Roberts:{angle} Roberts convolution kernel (3x3) | 0, 0, 0 | | -1, 1, 0 | | 0, 0, 0 | </dd>
174 <dd> Prewitt:{angle} Prewitt Edge convolution kernel (3x3) | -1, 0, 1 | | -1, 0, 1 | | -1, 0, 1 | </dd>
176 <dd> Compass:{angle} Prewitt's "Compass" convolution kernel (3x3) | -1, 1, 1 | | -1,-2, 1 | | -1, 1, 1 | </dd>
178 <dd> Kirsch:{angle} Kirsch's "Compass" convolution kernel (3x3) | -3,-3, 5 | | -3, 0, 5 | | -3,-3, 5 | </dd
    [all...]
  /external/ImageMagick/www/api/
morphology.html 63 <p>AcquireKernelInfo() takes the given string (generally supplied by the user) and converts it into a Morphology/Convolution Kernel. This allows users to specify a kernel from a number of pre-defined kernels, or to fully specify their own kernel for a specific Convolution or Morphology Operation.</p>
105 <dd>the Morphology/Convolution kernel wanted. </dd>
136 <dd> Convolution Kernels </dd>
166 <dd> Named Constant Convolution Kernels </dd>
174 <dd> Sobel:{angle} Sobel 'Edge' convolution kernel (3x3) | -1, 0, 1 | | -2, 0,-2 | | -1, 0, 1 | </dd>
176 <dd> Roberts:{angle} Roberts convolution kernel (3x3) | 0, 0, 0 | | -1, 1, 0 | | 0, 0, 0 | </dd>
178 <dd> Prewitt:{angle} Prewitt Edge convolution kernel (3x3) | -1, 0, 1 | | -1, 0, 1 | | -1, 0, 1 | </dd>
180 <dd> Compass:{angle} Prewitt's "Compass" convolution kernel (3x3) | -1, 1, 1 | | -1,-2, 1 | | -1, 1, 1 | </dd>
182 <dd> Kirsch:{angle} Kirsch's "Compass" convolution kernel (3x3) | -3,-3, 5 | | -3, 0, 5 | | -3,-3, 5 | </dd
    [all...]
morphology.php 59 <p>AcquireKernelInfo() takes the given string (generally supplied by the user) and converts it into a Morphology/Convolution Kernel. This allows users to specify a kernel from a number of pre-defined kernels, or to fully specify their own kernel for a specific Convolution or Morphology Operation.</p>
101 <dd>the Morphology/Convolution kernel wanted. </dd>
132 <dd> Convolution Kernels </dd>
162 <dd> Named Constant Convolution Kernels </dd>
170 <dd> Sobel:{angle} Sobel 'Edge' convolution kernel (3x3) | -1, 0, 1 | | -2, 0,-2 | | -1, 0, 1 | </dd>
172 <dd> Roberts:{angle} Roberts convolution kernel (3x3) | 0, 0, 0 | | -1, 1, 0 | | 0, 0, 0 | </dd>
174 <dd> Prewitt:{angle} Prewitt Edge convolution kernel (3x3) | -1, 0, 1 | | -1, 0, 1 | | -1, 0, 1 | </dd>
176 <dd> Compass:{angle} Prewitt's "Compass" convolution kernel (3x3) | -1, 1, 1 | | -1,-2, 1 | | -1, 1, 1 | </dd>
178 <dd> Kirsch:{angle} Kirsch's "Compass" convolution kernel (3x3) | -3,-3, 5 | | -3, 0, 5 | | -3,-3, 5 | </dd
    [all...]
  /external/tensorflow/tensorflow/compiler/tests/
depthwise_conv_op_test.py 36 # Reference implementation of depthwise convolution that uses regular
37 # convolution.
64 """Iterator for different convolution shapes, strides and paddings.
68 convolution parameters.
91 """Iterator for different convolution shapes, strides and paddings.
98 convolution parameters.
131 """Verifies the output values of the convolution function.
227 """Verifies the output values of the depthwise convolution function.
  /external/tensorflow/tensorflow/contrib/lite/kernels/
kernel_util.h 74 // Calculates the multiplication factor for a quantized convolution (or
75 // quantized depthwise convolution) involving the given tensors. Returns an
  /external/tensorflow/tensorflow/contrib/model_pruning/python/layers/
layers.py 115 """Adds an 2D convolution followed by an optional batch_norm layer.
117 the convolution operation is the elementwise multiplication of the mask
122 `convolution` creates a variable called `weights`, representing the
130 Performs atrous convolution with input stride/dilation rate equal to `rate`
156 for atrous convolution. Can be a single integer to specify the same
201 raise ValueError('Sparse Convolution not supported for input with rank',
206 raise ValueError('Sparse Convolution not supported for input with rank',
209 raise ValueError('Sparse Convolution not supported for input with rank',
  /external/tensorflow/tensorflow/core/api_def/base_api/
api_def_SpaceToBatch.pbtxt 95 Among others, this operation is useful for reducing atrous convolution into
96 regular convolution.
api_def_SpaceToBatchND.pbtxt 125 Among others, this operation is useful for reducing atrous convolution into
126 regular convolution.
api_def_Conv3D.pbtxt 49 summary: "Computes a 3-D convolution given 5-D `input` and `filter` tensors."
api_def_Conv3DBackpropFilterV2.pbtxt 58 summary: "Computes the gradients of 3-D convolution with respect to the filter."
api_def_Conv3DBackpropInputV2.pbtxt 58 summary: "Computes the gradients of 3-D convolution with respect to the input."
api_def_DepthwiseConv2dNative.pbtxt 36 summary: "Computes a 2-D depthwise convolution given 4-D `input` and `filter` tensors."
api_def_FusedPadConv2D.pbtxt 36 summary: "Performs a padding as a preprocess during a convolution."
api_def_QuantizedConv2D.pbtxt 68 summary: "Computes a 2D convolution given quantized 4D input and filter tensors."
  /external/tensorflow/tensorflow/docs_src/tutorials/
pdes.md 51 """Transform a 2D array into a convolution kernel"""
57 """A simplified 2D convolution operation"""
  /external/mesa3d/docs/relnotes/
6.2 22 ToDo: PBO for polygon stipple, convolution filter, etc.
  /external/tensorflow/tensorflow/compiler/xla/service/cpu/
ir_emission_utils.h 26 const HloInstruction& convolution);
  /external/tensorflow/tensorflow/compiler/xla/tests/
sample_file_test.cc 43 TEST_F(SampleFileTest, Convolution) {
  /external/tensorflow/tensorflow/core/kernels/
xsmm_conv2d.h 31 // Returns true if convolution operation specified by function arguments
  /external/tensorflow/tensorflow/core/util/
use_cudnn.h 23 // FP16ConvMode: The mode to set the internal compute type for cudnn convolution

Completed in 536 milliseconds

1 23 4 5 6 7 8 91011>>