1

我试图用 Tensorflow 构建一个变分自动编码器。我从最简单的模型开始。我有以下方法：

def conv_layer(x, w_shape, b_shape, padding='SAME'):
    W = weight_variable(w_shape)
    tf.summary.histogram(W.name, W)

    b = bias_variable(b_shape)
    tf.summary.histogram(b.name, b)

    # Note that I used a stride of 2 on purpose in order not to use max pool layer.
    activations = tf.nn.relu(tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding=padding) + b)
    tf.summary.histogram(activations.name, activations)
    return activations

def deconv_layer(x, w_shape, b_shape, padding="SAME"):
    W = weight_variable(w_shape)
    tf.summary.histogram(W.name, W)

    b = bias_variable(b_shape)
    tf.summary.histogram('bias', b)

    x_shape = tf.shape(x)

    out_shape = tf.stack([x_shape[0], x_shape[1], x_shape[2], w_shape[2]])
    # Note that I have used a stride of 2 since I used a stride of 2 in conv layer.
    transposed_activations = tf.nn.conv2d_transpose(x, W, out_shape, [1, 1, 1, 1], padding=padding) + b
    tf.summary.histogram(transposed_activations.name, transposed_activations)
    return transposed_activations

整个网络的模型如下：

with tf.name_scope('conv1'):
    conv1 = conv_layer(image, [3, 3, 3, 32], [32])
with tf.name_scope('conv2'):
    conv2 = conv_layer(conv1, [3, 3, 32, 64], [64])
with tf.name_scope('conv3'):
    conv3 = conv_layer(conv2, [3, 3, 64, 128], [128])
with tf.name_scope('conv4'):
    conv4 = conv_layer(conv3, [3, 3, 128, 256], [256])

with tf.name_scope('z'):
    z = conv_layer(conv4, [3, 3, 256, 256], [256])

with tf.name_scope('deconv4'):
    deconv4 = deconv_layer(z, [3, 3, 128, 256], [128])
with tf.name_scope('deconv3'):
    deconv3 = deconv_layer(deconv4, [3, 3, 64, 128], [64])
with tf.name_scope('deconv2'):
    deconv2 = deconv_layer(deconv3, [3, 3, 32, 64], [32])
with tf.name_scope('deconv1'):
    deconv_image = deconv_layer(deconv2, [3, 3, 3, 32], [3])

我从 a 获取我的图像FIFOQueue并将它们输入到这个模型中。我的图像大小是112, 112, 3. 我的问题是从 conv和deconv[1, 1, 1, 1] to [1, 2, 2, 1]层中更改步幅时出现以下错误：

InvalidArgumentError (see above for traceback): Conv2DSlowBackpropInput: Size of out_backprop doesn't match computed: actual = 4, computed = 2
     [[Node: deconv4/conv2d_transpose = Conv2DBackpropInput[T=DT_FLOAT, data_format="NHWC", padding="SAME", strides=[1, 2, 2, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/gpu:0"](deconv4/stack, deconv4/Variable/read, z/Relu)]]
     [[Node: deconv1/add/_17 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name="edge_85_deconv1/add", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"]()]]

PS：我知道我在 deconv 层缺少激活函数，但我想这与我得到的错误无关。任何帮助深表感谢！！

4

1 回答 1

0

此错误的原因如下：

如果我们假设我们stride = 2在每个卷积层都有，那么，在我的情况下，当输入图像的大小为 时112, 112, 3，在每次应用卷积之后或之后conv layer的大小都会减少一半。即图像的大小（高度、宽度）变为. 之后，大小就变成了。之后：，之后：。因此，应用一个额外的命名已将维度减少到. 问题是：7 不能被 2 整除。所以我们得到了不同的维度。申请后从到是不可能的。此外： framesfeature mapsconv1[56, 56]conv2[28, 28]conv3[14, 14]conv4[7, 7]conv layerz[3, 3][3, 3][112, 112]deconv layer

[3, 3] -> [6, 6] -> [12, 12] -> [24, 24] -> [48, 48]

第二个错误： 中的输出形状deconv layer应该如下：

# we should multiply x_shape[1] and x_shape[2] by 2. 
out_shape = tf.stack([x_shape[0], x_shape[1] * 2, x_shape[2] * 2, w_shape[2]])

因此，最终deconv layer变成如下：

def deconv_layer(x, w_shape, b_shape, is_training, padding="SAME", activation='selu'):
    W = weight_variable(w_shape)
    tf.summary.histogram("weights", W)

    b = bias_variable(b_shape)
    tf.summary.histogram('biases', b)

    x_shape = tf.shape(x)
    # output shape: [batch_size, h * 2, w * 2, input_shape from w].
    out_shape = tf.stack([x_shape[0], x_shape[1] * 2, x_shape[2] * 2, w_shape[2]])
    # Note that I have used a stride of 2 since I used a stride of 2 in conv layer.
    if activation == 'selu':
        conv_trans = tf.nn.conv2d_transpose(x, W, out_shape, [1, 2, 2, 1], padding=padding) + b

        transposed_activations = tf.nn.elu(conv_trans)

    else:
        conv_trans = tf.nn.conv2d_transpose(x, W, out_shape, [1, 2, 2, 1], padding=padding) + b
        transposed_activations = tf.nn.sigmoid(conv_trans)

    tf.summary.histogram("transpose_activation", transposed_activations)
    return transposed_activations

因此，输出的大小与输入的大小不同，这就是我收到错误的原因。为了做到这一点，back propagation我们需要一个成本函数。该成本函数将取决于output和input。因此，如果它们具有不同的大小，则会导致错误。

解决这个问题的方法是让conv layer, z,to 拥有一个stride of 1.

于 2017-08-02T22:17:17.790 回答