prev_y = tf.placeholder( tf.float32, shape=[None, params.res["height"], params.res["width"]]) prev_y_in = tf.sub(tf.expand_dims(prev_y, 3), 0.5) x_in = tf.concat(3, [x, prev_y_in]) ch_in = 2 ############################## # Section 1 # Convolution layer_name = "s1_conv1" with tf.name_scope(layer_name): W = utils.weight_variable([k_size, k_size, ch_in, ch[0]]) b = utils.bias_variable([ch[0]]) conv = utils.conv2d(x_in, W, b, 1) tanh = tf.nn.tanh(conv) s1_conv1 = tf.nn.dropout(tanh, keep_prob) ############################## # Section 2 # Downsampling convolution layer_name = "s2_conv1" with tf.name_scope(layer_name): W = utils.weight_variable([k_size, k_size, ch[0], ch[1]]) b = utils.bias_variable([ch[1]]) conv = utils.conv2d(s1_conv1, W, b, 2) tanh = tf.nn.tanh(conv)
prev_y = tf.placeholder( tf.float32, shape=[None, params.res["height"], params.res["width"]]) prev_y_in = tf.sub(tf.expand_dims(prev_y, 3), 0.5) x_in = tf.concat(3, [x, prev_y_in]) ch_in = 2 ############################## # Section 1 # Convolution layer_name = "s1_conv1_1" with tf.name_scope(layer_name): W = utils.weight_variable([5, 5, ch_in, ch[0]]) b = utils.bias_variable([ch[0]]) conv = utils.conv2d(x_in, W, b, 1) tanh = tf.nn.tanh(conv) s1_conv1_1 = tf.nn.dropout(tanh, keep_prob) ############################## # Section 2 # Asymmetric convolution (1x5) layer_name = "s2_conv1_1" with tf.name_scope(layer_name): W = utils.weight_variable([1, 5, ch[0], ch[1]]) b = utils.bias_variable([ch[1]]) conv = utils.conv2d(s1_conv1_1, W, b, 1) tanh = tf.nn.tanh(conv)
y_ = tf.placeholder(tf.bool, shape=[None, params.res["height"], params.res["width"]]) prev_y = tf.placeholder(tf.float32, shape=[None, params.res["height"], params.res["width"]]) prev_y_in = tf.sub(tf.expand_dims(prev_y, 3), 0.5) x_in = tf.concat(3, [x, prev_y_in]) ch_in = 2 ############################## # Section 1 # Convolution layer_name = "s1_conv1" with tf.name_scope(layer_name): W = utils.weight_variable([k_size, k_size, ch_in, ch[0]]) b = utils.bias_variable([ch[0]]) conv = utils.conv2d(x_in, W, b, 1) tanh = tf.nn.tanh(conv) s1_conv1 = tf.nn.dropout(tanh, keep_prob) ############################## # Section 2 # Downsampling convolution layer_name = "s2_conv1" with tf.name_scope(layer_name): W = utils.weight_variable([k_size, k_size, ch[0], ch[1]]) b = utils.bias_variable([ch[1]]) conv = utils.conv2d(s1_conv1, W, b, 2)
prev_y = tf.placeholder( tf.float32, shape=[None, params.res["height"], params.res["width"]]) prev_y_in = tf.sub(tf.expand_dims(prev_y, 3), 0.5) x_in = tf.concat(3, [x, prev_y_in]) ch_in = 2 ############################## # Section 1 # Convolution layer_name = "s1_conv1" with tf.name_scope(layer_name): W = utils.weight_variable([k_size, k_size, ch_in, ch]) b = utils.bias_variable([ch]) conv = utils.conv2d(x_in, W, b, 1) tanh = tf.nn.tanh(conv) s1_conv1 = tf.nn.dropout(tanh, keep_prob) # Convolution layer_name = "s1_conv2" with tf.name_scope(layer_name): W = utils.weight_variable([k_size, k_size, ch, ch]) b = utils.bias_variable([ch]) conv = utils.conv2d(s1_conv1, W, b, 1) tanh = tf.nn.tanh(conv) s1_conv2 = tf.nn.dropout(tanh, keep_prob) # Convolution