如何将此张量流代码转换为 pytorch 代码?

时间:2021-06-11 17:06:36

标签: python tensorflow deep-learning pytorch generative-adversarial-network

我正在尝试实现一个用 tensorflow 编写到 pytorch 的图像去噪 Gan,但我无法理解 pytorch 中 tf.variable_scopetf.Variable 的相似之处。请帮忙。

def conv_layer(input_image, ksize, in_channels, out_channels, stride, scope_name, activation_function=lrelu, reuse=False):
    with tf.variable_scope(scope_name):
        filter = tf.Variable(tf.random_normal([ksize, ksize, in_channels, out_channels], stddev=0.03))
        output = tf.nn.conv2d(input_image, filter, strides=[1, stride, stride, 1], padding='SAME')
        output = slim.batch_norm(output)
        if activation_function:
            output = activation_function(output)
        return output, filter
def residual_layer(input_image, ksize, in_channels, out_channels, stride, scope_name):
    with tf.variable_scope(scope_name):
        output, filter = conv_layer(input_image, ksize, in_channels, out_channels, stride, scope_name+"_conv1")
        output, filter = conv_layer(output, ksize, out_channels, out_channels, stride, scope_name+"_conv2")
        output = tf.add(output, tf.identity(input_image))
        return output, filter

def transpose_deconvolution_layer(input_tensor, used_weights, new_shape, stride, scope_name):
    with tf.varaible_scope(scope_name):
        output = tf.nn.conv2d_transpose(input_tensor, used_weights, output_shape=new_shape, strides=[1, stride, stride, 1], padding='SAME')
        output = tf.nn.relu(output)
        return output

def resize_deconvolution_layer(input_tensor, new_shape, scope_name):
    with tf.variable_scope(scope_name):
        output = tf.image.resize_images(input_tensor, (new_shape[1], new_shape[2]), method=1)
        output, unused_weights = conv_layer(output, 3, new_shape[3]*2, new_shape[3], 1, scope_name+"_deconv")
        return output

1 个答案:

答案 0 :(得分:1)

您可以将 tf.Variable 替换为 torch.tensortorch.tensor 可以保持相同的渐变。

在 torch 中,您也不会创建图形,然后通过某个范围按名称访问其中的内容。您只需创建张量,然后就可以直接访问它。那里的 output 变量可以让您随心所欲地使用它,并可以随心所欲地重复使用。

事实上,如果你的代码没有直接使用这个变量作用域,那么你可以忽略它。如果您要检查图形,变量作用域通常只是为了给事物提供方便的名称。