我们从Python开源项目中，提取了以下8个代码示例，用于说明如何使用tensorflow.contrib.layers.convolution2d_transpose()。
def conv_generator(x, output_dim, n_filters, scope='Generator'): with tf.variable_scope(scope): s4, s2 = int(output_dim / 4), int(output_dim / 2) z_ = layers.linear(x, s4 * s4 * n_filters * 2) h0 = tf.reshape(z_, [-1, s4, s4, n_filters * 2]) h1 = layers.convolution2d_transpose(h0, n_filters, [5, 5], stride=2) h1 = tf.nn.elu(h1) h2 = layers.convolution2d_transpose(h1, 1, [5, 5], stride=2) return tf.reshape(tf.nn.tanh(h2), [-1, output_dim * output_dim])
def get_network(self, input_tensor, is_training): # Load pre-trained inception-resnet model with slim.arg_scope(inception_resnet_v2_arg_scope(batch_norm_decay = 0.999, weight_decay = 0.0001)): net, end_points = inception_resnet_v2(input_tensor, is_training = is_training) # Adding some modification to original InceptionResnetV2 - changing scoring of AUXILIARY TOWER weight_decay = 0.0005 with tf.variable_scope('NewInceptionResnetV2'): with tf.variable_scope('AuxiliaryScoring'): with slim.arg_scope([layers.convolution2d, layers.convolution2d_transpose], weights_regularizer = slim.l2_regularizer(weight_decay), biases_regularizer = slim.l2_regularizer(weight_decay), activation_fn = None): tf.summary.histogram('Last_layer/activations', net, [KEY_SUMMARIES]) # Scoring net = slim.dropout(net, 0.7, is_training = is_training, scope = 'Dropout') net = layers.convolution2d(net, num_outputs = self.FEATURES, kernel_size = 1, stride = 1, scope = 'Scoring_layer') feature = net tf.summary.histogram('Scoring_layer/activations', net, [KEY_SUMMARIES]) # Upsampling net = layers.convolution2d_transpose(net, num_outputs = 16, kernel_size = 17, stride = 17, padding = 'VALID', scope = 'Upsampling_layer') tf.summary.histogram('Upsampling_layer/activations', net, [KEY_SUMMARIES]) # Smoothing layer - separable gaussian filters net = super()._get_gauss_smoothing_net(net, size = self.SMOOTH_SIZE, std = 1.0, kernel_sum = 0.2) return net, feature
def netG(z, y, BATCH_SIZE): # concat attribute y onto z z = tf.concat([z,y], axis=1) z = tcl.fully_connected(z, 4*4*512, activation_fn=tf.identity, scope='g_z') #z = tcl.batch_norm(z) z = tf.reshape(z, [BATCH_SIZE, 4, 4, 512]) #z = tf.nn.relu(z) conv1 = tcl.convolution2d_transpose(z, 256, 5, 2, normalizer_fn=tcl.batch_norm, activation_fn=tf.nn.relu, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='g_conv1') conv2 = tcl.convolution2d_transpose(conv1, 128, 5, 2, normalizer_fn=tcl.batch_norm, activation_fn=tf.nn.relu, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='g_conv2') conv3 = tcl.convolution2d_transpose(conv2, 64, 5, 2, normalizer_fn=tcl.batch_norm, activation_fn=tf.nn.relu, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='g_conv3') conv4 = tcl.convolution2d_transpose(conv3, 3, 5, 2, activation_fn=tf.nn.tanh, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='g_conv4') print 'z:',z print 'conv1:',conv1 print 'conv2:',conv2 print 'conv3:',conv3 print 'conv4:',conv4 print print 'END G' print tf.add_to_collection('vars', z) tf.add_to_collection('vars', conv1) tf.add_to_collection('vars', conv2) tf.add_to_collection('vars', conv3) tf.add_to_collection('vars', conv4) return conv4
def netG(z, y, BATCH_SIZE): # concat attribute y onto z z = tf.concat([z,y], axis=1) print 'z:',z z = tcl.fully_connected(z, 4*4*512, activation_fn=tf.identity, scope='g_z') z = tf.reshape(z, [BATCH_SIZE, 4, 4, 512]) z = tcl.batch_norm(z) z = tf.nn.relu(z) conv1 = tcl.convolution2d_transpose(z, 256, 5, 2, normalizer_fn=tcl.batch_norm, activation_fn=tf.nn.relu, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='g_conv1') conv2 = tcl.convolution2d_transpose(conv1, 128, 5, 2, normalizer_fn=tcl.batch_norm, activation_fn=tf.nn.relu, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='g_conv2') conv3 = tcl.convolution2d_transpose(conv2, 1, 5, 2, normalizer_fn=tcl.batch_norm, activation_fn=tf.nn.relu, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='g_conv3') conv3 = conv3[:,:28,:28,:] print 'z:',z print 'conv1:',conv1 print 'conv2:',conv2 print 'conv3:',conv3 print print 'END G' print tf.add_to_collection('vars', z) tf.add_to_collection('vars', conv1) tf.add_to_collection('vars', conv2) tf.add_to_collection('vars', conv3) return conv3
def deconv2d(input_, o_size, k_size, name='deconv2d'): print name, 'input', ten_sh(input_) print name, 'output', o_size assert np.sum(np.mod(o_size[1:3], ten_sh(input_)[1:3]) - [0,0]) == 0 with tf.variable_scope(name): init = ly.xavier_initializer_conv2d() output = ly.convolution2d_transpose(input_, num_outputs=o_size[-1], \ kernel_size=k_size, stride=np.divide(o_size[1:3], ten_sh(input_)[1:3]), \ padding='SAME', weights_initializer=init) return output
def deconv2d(input_, o_size, k_size, name='deconv2d'): print name, 'input', ten_sh(input_) print name, 'output', o_size assert np.sum(np.mod(o_size[1:3], ten_sh(input_)[1:3]) - [0,0]) == 0 with tf.variable_scope(name): init = ly.xavier_initializer_conv2d() output = ly.convolution2d_transpose(input_, num_outputs=o_size[-1], \ kernel_size=k_size, stride=np.divide(o_size[1:3], ten_sh(input_)[1:3]), \ padding='SAME', weights_initializer=init, \ activation_fn=tf.nn.relu, normalizer_fn=ly.batch_norm) return output
def decoder(layers, y, BATCH_SIZE): layers = layers[0] # get all the layers from the encoder for skip connections. enc_conv1 = layers[0] enc_conv2 = layers[1] enc_conv3 = layers[2] enc_conv4 = layers[3] enc_conv5 = layers[4] enc_conv6 = layers[5] ''' print 'enc_conv1:',enc_conv1 print 'enc_conv2:',enc_conv2 print 'enc_conv3:',enc_conv3 print 'enc_conv4:',enc_conv4 print 'enc_conv5:',enc_conv5 print 'enc_conv6:',enc_conv6 ''' # z is the latent encoding (conv6) z = tcl.flatten(layers[-1]) z = tf.concat([z,y], axis=1) print 'z:',z # reshape z to put through transpose convolutions s = z.get_shape().as_list()[-1] z = tf.reshape(z, [BATCH_SIZE, 1, 1, s]) print 'z:',z dec_conv1 = tcl.convolution2d_transpose(z, 512, 4, 2, activation_fn=tf.nn.relu, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='g_dec_conv1') #dec_conv1 = tf.concat([dec_conv1, enc_conv5], axis=3) print 'dec_conv1:',dec_conv1 dec_conv2 = tcl.convolution2d_transpose(dec_conv1, 512, 4, 2, activation_fn=tf.nn.relu, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='g_dec_conv2') #dec_conv2 = tf.concat([dec_conv2, enc_conv4], axis=3) print 'dec_conv2:',dec_conv2 dec_conv3 = tcl.convolution2d_transpose(dec_conv2, 256, 4, 2, activation_fn=tf.nn.relu, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='g_dec_conv3') #dec_conv3 = tf.concat([dec_conv3, enc_conv3], axis=3) print 'dec_conv3:',dec_conv3 dec_conv4 = tcl.convolution2d_transpose(dec_conv3, 128, 4, 2, activation_fn=tf.nn.relu, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='g_dec_conv4') #dec_conv3 = tf.concat([dec_conv4, enc_conv2], axis=3) print 'dec_conv4:',dec_conv4 dec_conv5 = tcl.convolution2d_transpose(dec_conv4, 64, 4, 2, activation_fn=tf.nn.relu, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='g_dec_conv5') #dec_conv3 = tf.concat([dec_conv5, enc_conv1], axis=3) print 'dec_conv5:',dec_conv5 dec_conv6 = tcl.convolution2d_transpose(dec_conv5, 3, 4, 2, activation_fn=tf.nn.relu, weights_initializer=tf.random_normal_initializer(stddev=0.02), scope='g_dec_conv6') print 'dec_conv6:',dec_conv6 print print 'END G' print return dec_conv6
