/external/tensorflow/tensorflow/contrib/slim/python/slim/nets/ |
D | inception_v3.py | 107 [layers.conv2d, layers_lib.max_pool2d, layers_lib.avg_pool2d], 112 net = layers.conv2d(inputs, depth(32), [3, 3], stride=2, scope=end_point) 118 net = layers.conv2d(net, depth(32), [3, 3], scope=end_point) 124 net = layers.conv2d( 137 net = layers.conv2d(net, depth(80), [1, 1], scope=end_point) 143 net = layers.conv2d(net, depth(192), [3, 3], scope=end_point) 157 [layers.conv2d, layers_lib.max_pool2d, layers_lib.avg_pool2d], 164 branch_0 = layers.conv2d( 167 branch_1 = layers.conv2d( 169 branch_1 = layers.conv2d( [all …]
|
D | inception_v1.py | 62 [layers.conv2d, layers_lib.fully_connected], 65 [layers.conv2d, layers_lib.max_pool2d], stride=1, padding='SAME'): 67 net = layers.conv2d(inputs, 64, [7, 7], stride=2, scope=end_point) 77 net = layers.conv2d(net, 64, [1, 1], scope=end_point) 82 net = layers.conv2d(net, 192, [3, 3], scope=end_point) 95 branch_0 = layers.conv2d(net, 64, [1, 1], scope='Conv2d_0a_1x1') 97 branch_1 = layers.conv2d(net, 96, [1, 1], scope='Conv2d_0a_1x1') 98 branch_1 = layers.conv2d( 101 branch_2 = layers.conv2d(net, 16, [1, 1], scope='Conv2d_0a_1x1') 102 branch_2 = layers.conv2d( [all …]
|
D | inception_v2.py | 84 layers.conv2d, layers_lib.max_pool2d, layers_lib.avg_pool2d, 121 net = layers.conv2d( 131 net = layers.conv2d(net, depth(192), [3, 3], scope=end_point) 146 branch_0 = layers.conv2d( 149 branch_1 = layers.conv2d( 154 branch_1 = layers.conv2d( 157 branch_2 = layers.conv2d( 162 branch_2 = layers.conv2d( 164 branch_2 = layers.conv2d( 168 branch_3 = layers.conv2d( [all …]
|
D | vgg.py | 66 [layers.conv2d, layers_lib.fully_connected], 70 with arg_scope([layers.conv2d], padding='SAME') as arg_sc: 102 [layers.conv2d, layers_lib.max_pool2d], 105 inputs, 1, layers.conv2d, 64, [3, 3], scope='conv1') 107 net = layers_lib.repeat(net, 1, layers.conv2d, 128, [3, 3], scope='conv2') 109 net = layers_lib.repeat(net, 2, layers.conv2d, 256, [3, 3], scope='conv3') 111 net = layers_lib.repeat(net, 2, layers.conv2d, 512, [3, 3], scope='conv4') 113 net = layers_lib.repeat(net, 2, layers.conv2d, 512, [3, 3], scope='conv5') 116 net = layers.conv2d(net, 4096, [7, 7], padding='VALID', scope='fc6') 119 net = layers.conv2d(net, 4096, [1, 1], scope='fc7') [all …]
|
D | overfeat.py | 50 [layers.conv2d, layers_lib.fully_connected], 54 with arg_scope([layers.conv2d], padding='SAME'): 96 [layers.conv2d, layers_lib.fully_connected, layers_lib.max_pool2d], 98 net = layers.conv2d( 101 net = layers.conv2d(net, 256, [5, 5], padding='VALID', scope='conv2') 103 net = layers.conv2d(net, 512, [3, 3], scope='conv3') 104 net = layers.conv2d(net, 1024, [3, 3], scope='conv4') 105 net = layers.conv2d(net, 1024, [3, 3], scope='conv5') 108 [layers.conv2d], 112 net = layers.conv2d(net, 3072, [6, 6], padding='VALID', scope='fc6') [all …]
|
D | alexnet.py | 54 [layers.conv2d, layers_lib.fully_connected], 58 with arg_scope([layers.conv2d], padding='SAME'): 99 [layers.conv2d, layers_lib.fully_connected, layers_lib.max_pool2d], 101 net = layers.conv2d( 104 net = layers.conv2d(net, 192, [5, 5], scope='conv2') 106 net = layers.conv2d(net, 384, [3, 3], scope='conv3') 107 net = layers.conv2d(net, 384, [3, 3], scope='conv4') 108 net = layers.conv2d(net, 256, [3, 3], scope='conv5') 113 [layers.conv2d], 116 net = layers.conv2d(net, 4096, [5, 5], padding='VALID', scope='fc6') [all …]
|
D | resnet_v2.py | 105 shortcut = layers_lib.conv2d( 113 residual = layers_lib.conv2d( 117 residual = layers_lib.conv2d( 200 [layers_lib.conv2d, bottleneck, resnet_utils.stack_blocks_dense], 213 [layers_lib.conv2d], activation_fn=None, normalizer_fn=None): 226 net = layers_lib.conv2d(
|
D | resnet_v1.py | 109 shortcut = layers.conv2d( 116 residual = layers.conv2d( 120 residual = layers.conv2d( 196 [layers.conv2d, bottleneck, resnet_utils.stack_blocks_dense], 212 net = layers.conv2d(
|
D | resnet_utils.py | 124 return layers_lib.conv2d( 139 return layers_lib.conv2d( 256 [layers_lib.conv2d],
|
/external/tensorflow/tensorflow/core/grappler/optimizers/ |
D | remapper.cc | 74 Conv2DWithBiasAdd(const NodeDef* conv2d, const NodeDef* bias_add) in Conv2DWithBiasAdd() 75 : conv2d(conv2d), bias_add(bias_add) {} in Conv2DWithBiasAdd() 77 const NodeDef* conv2d = nullptr; member 84 Conv2DWithBiasAddAndRelu(const NodeDef* conv2d, const NodeDef* bias_add, in Conv2DWithBiasAddAndRelu() 86 : conv2d(conv2d), bias_add(bias_add), relu(relu) {} in Conv2DWithBiasAddAndRelu() 88 const NodeDef* conv2d = nullptr; member 96 Conv2DWithSqueezeAndBiasAdd(const NodeDef* conv2d, const NodeDef* squeeze, in Conv2DWithSqueezeAndBiasAdd() 98 : conv2d(conv2d), squeeze(squeeze), bias_add(bias_add) {} in Conv2DWithSqueezeAndBiasAdd() 100 const NodeDef* conv2d = nullptr; member 108 Conv2DWithBatchNorm(const NodeDef* conv2d, const NodeDef* fused_batch_norm, in Conv2DWithBatchNorm() [all …]
|
/external/tensorflow/tensorflow/contrib/receptive_field/python/util/ |
D | receptive_field_test.py | 51 l1 = slim.conv2d(x, 1, [1, 1], stride=4, scope='L1', padding='VALID') 54 l2 = slim.conv2d(l2_pad, 1, [3, 3], stride=2, scope='L2', padding='VALID') 55 l3 = slim.conv2d(l2, 1, [1, 1], stride=2, scope='L3', padding='VALID') 79 l1 = slim.conv2d(x, 1, [1, 1], stride=4, scope='L1', padding='VALID') 105 l1 = slim.conv2d(l1_pad, 1, [5, 5], stride=2, scope='L1', padding='VALID') 107 l2 = slim.conv2d(x, 1, [3, 3], stride=1, scope='L2', padding='VALID') 108 l3 = slim.conv2d(l2, 1, [3, 3], stride=1, scope='L3', padding='VALID') 132 l1 = slim.conv2d(x, 1, [1, 1], stride=4, scope='L1', padding='VALID') 134 l2 = slim.conv2d(x, 1, [3, 3], stride=2, scope='L2', padding='SAME') 135 l3 = slim.conv2d(l2, 1, [1, 1], stride=2, scope='L3', padding='VALID') [all …]
|
D | graph_compute_order_test.py | 43 l1 = slim.conv2d(x, 1, [1, 1], stride=4, scope='L1', padding='VALID') 46 l2 = slim.conv2d(l2_pad, 1, [3, 3], stride=2, scope='L2', padding='VALID') 51 l5 = slim.conv2d(l4, 1, [1, 1], stride=2, scope='L5', padding='SAME') 53 l6 = slim.conv2d(l4, 1, [3, 3], stride=2, scope='L6', padding='SAME')
|
D | parse_layer_parameters_test.py | 45 l1 = slim.conv2d(x, 1, [1, 1], stride=4, scope='L1', padding='VALID') 48 l2 = slim.conv2d(l2_pad, 1, [3, 3], stride=2, scope='L2', padding='VALID') 53 l5 = slim.conv2d(l4, 1, [1, 1], stride=2, scope='L5', padding='SAME') 55 l6 = slim.conv2d(l4, 1, [3, 3], stride=2, scope='L6', padding='SAME')
|
/external/tensorflow/tensorflow/contrib/quantize/python/ |
D | quantize_test.py | 36 conv2d = layers.conv2d variable 55 conv = conv2d(inputs, 32, [5, 5], stride=2, padding='SAME', 77 conv = conv2d(input1, 32, [5, 5], stride=2, padding='SAME', 207 _ = conv2d( 234 _ = conv2d( 257 conv = conv2d( 267 _ = conv2d( 295 conv1 = conv2d( 306 conv2 = conv2d( 354 _ = conv2d( [all …]
|
D | common_test.py | 34 conv2d = layers.conv2d variable 103 node = conv2d(
|
/external/tensorflow/tensorflow/contrib/specs/python/ |
D | specs_ops.py | 80 Cx = Fun(layers.conv2d) 81 Cs = Fun(layers.conv2d, activation_fn=math_ops.sigmoid) 82 Ct = Fun(layers.conv2d, activation_fn=math_ops.tanh) 83 Cr = Fun(layers.conv2d, activation_fn=nn_ops.relu) 84 Cm = Fun(layers.conv2d, activation_fn=nn_ops.softmax) 85 Cl = Fun(layers.conv2d, activation_fn=None)
|
/external/tensorflow/tensorflow/python/profiler/internal/ |
D | model_analyzer_testlib.py | 49 x = nn_ops.conv2d(image, kernel, [1, 2, 2, 1], padding='SAME') 54 x = nn_ops.conv2d(x, kernel, [1, 2, 2, 1], padding='SAME') 83 r1 = nn_ops.conv2d(image, kernel1, [1, 2, 2, 1], padding='SAME') 89 r2 = nn_ops.conv2d(image, kernel2, [1, 2, 2, 1], padding='SAME')
|
/external/tensorflow/tensorflow/contrib/slim/ |
D | README.md | 120 created by a `slim.fully_connected` or `slim.conv2d` layer. Non-model variables 185 conv = tf.nn.conv2d(input, kernel, [1, 1, 1, 1], padding='SAME') 199 net = slim.conv2d(input, 128, [3, 3], scope='conv1_1') 209 Conv2d | [slim.conv2d](https://www.tensorflow.org/code/tensorflow/contrib/layers/python/layers/laye… 229 net = slim.conv2d(net, 256, [3, 3], scope='conv3_1') 230 net = slim.conv2d(net, 256, [3, 3], scope='conv3_2') 231 net = slim.conv2d(net, 256, [3, 3], scope='conv3_3') 240 net = slim.conv2d(net, 256, [3, 3], scope='conv3_%d' % (i+1)) 247 net = slim.repeat(net, 3, slim.conv2d, 256, [3, 3], scope='conv3') 253 subsequent call of `slim.conv2d` are appended with an underscore and iteration [all …]
|
/external/tensorflow/tensorflow/python/compiler/tensorrt/test/ |
D | const_broadcast_test.py | 45 y1 = nn.conv2d(x, filt1, strides=[1, 1, 1, 1], padding='SAME', name='y1') 49 y2 = nn.conv2d(z1, filt2, strides=[1, 1, 1, 1], padding='SAME', name='y2') 56 y3 = nn.conv2d(z2, filt3, strides=[1, 1, 1, 1], padding='SAME', name='y3')
|
D | memory_alignment_test.py | 49 conv = nn.conv2d( 55 out = nn.conv2d(
|
/external/tensorflow/tensorflow/python/kernel_tests/ |
D | conv_ops_test.py | 213 conv = nn_ops.conv2d( 248 conv = nn_ops.conv2d( 287 computed = nn_ops.conv2d( 393 conv2d_result = nn_ops.conv2d( 1091 conv_forward = nn_ops.conv2d( 1137 conv_forward = nn_ops.conv2d( 1685 conv = nn_ops.conv2d( 2243 c1 = nn_ops.conv2d( 2252 nn_ops.conv2d( 2261 nn_ops.conv2d( [all …]
|
D | atrous_conv2d_test.py | 82 y2 = nn_ops.conv2d( 134 y2 = nn_ops.conv2d(y2, f, strides=[1, 1, 1, 1], padding=padding) 135 y2 = nn_ops.conv2d(y2, f, strides=[1, 1, 1, 1], padding=padding) 136 y2 = nn_ops.conv2d(y2, f, strides=[1, 1, 1, 1], padding=padding)
|
/external/tensorflow/tensorflow/core/kernels/ |
D | conv_ops_test.cc | 1068 Node* conv2d; member 1073 Node* conv2d; member 1079 Node* conv2d; member 1086 Node* conv2d; member 1092 Node* conv2d; member 1114 Node* conv2d; in Conv2D() local 1121 .Finalize(graph, &conv2d)); in Conv2D() 1123 return {graph, conv2d}; in Conv2D() 1134 Node* conv2d = conv_graph.conv2d; in Conv2DWithBias() local 1141 .Input(conv2d) in Conv2DWithBias() [all …]
|
/external/tensorflow/tensorflow/python/ops/ |
D | conv2d_benchmark.py | 72 conv2d_op = nn_ops.conv2d( 77 conv2d_op = nn_ops.conv2d( 82 warmup_conv2d_op = nn_ops.conv2d( 87 warmup_conv2d_op = nn_ops.conv2d(
|
/external/tensorflow/tensorflow/python/tools/ |
D | optimize_for_inference_test.py | 140 conv_op = nn_ops.conv2d( 187 conv_op = nn_ops.conv2d( 240 nn_ops.conv2d( 270 nn_ops.conv2d( 300 nn_ops.conv2d(
|