Question

我在tensorflow中创建了一个2 CN层+密集层网络。当我运行程序，过滤器大小为32，内核大小为3 x 3时，我的准确度大约为97％。但是当我为CN层1和CN层2运行此程序的过滤器大小为10时，它会给出一个值错误。

这是我的代码：

＆＃13;

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import numpy as np
import tensorflow as tf

tf.logging.set_verbosity(tf.logging.INFO)


def cnn_model_fn(features, labels, mode):
  """Model function for CNN."""
  # Input Layer
  # Reshape X to 4-D tensor: [batch_size, width, height, channels]
  # MNIST images are 28x28 pixels, and have one color channel
  input_layer = tf.reshape(features["x"], [-1, 28, 28, 1])

  # Convolutional Layer #1
  # Computes 32 features using a 5x5 filter with ReLU activation.
  # Padding is added to preserve width and height.
  # Input Tensor Shape: [batch_size, 28, 28, 1]
  # Output Tensor Shape: [batch_size, 28, 28, 32]
  conv1 = tf.layers.conv2d(
      inputs=input_layer,
      filters=10,
      kernel_size=[3, 3],
      padding="same",
      activation=tf.nn.relu)

  # Pooling Layer #1
  # First max pooling layer with a 2x2 filter and stride of 2
  # Input Tensor Shape: [batch_size, 28, 28, 32]
  # Output Tensor Shape: [batch_size, 14, 14, 32]
  pool1 = tf.layers.max_pooling2d(inputs=conv1, pool_size=[2, 2], strides=2)

  # Convolutional Layer #2
  # Computes 64 features using a 5x5 filter.
  # Padding is added to preserve width and height.
  # Input Tensor Shape: [batch_size, 14, 14, 32]
  # Output Tensor Shape: [batch_size, 14, 14, 64]
  conv2 = tf.layers.conv2d(
      inputs=pool1,
      filters=10,
      kernel_size=[3, 3],
      padding="same",
      activation=tf.nn.relu)

  # Pooling Layer #2
  # Second max pooling layer with a 2x2 filter and stride of 2
  # Input Tensor Shape: [batch_size, 14, 14, 64]
  # Output Tensor Shape: [batch_size, 7, 7, 64]
  pool2 = tf.layers.max_pooling2d(inputs=conv2, pool_size=[2, 2], strides=2)

  # Flatten tensor into a batch of vectors
  # Input Tensor Shape: [batch_size, 7, 7, 64]
  # Output Tensor Shape: [batch_size, 7 * 7 * 64]
  pool2_flat = tf.reshape(pool2, [-1, 7 * 7 * 64])

  # Dense Layer
  # Densely connected layer with 1024 neurons
  # Input Tensor Shape: [batch_size, 7 * 7 * 64]
  # Output Tensor Shape: [batch_size, 1024]
  dense = tf.layers.dense(inputs=pool2_flat, units=1024, activation=tf.nn.relu)

  # Add dropout operation; 0.6 probability that element will be kept
  dropout = tf.layers.dropout(
      inputs=dense, rate=0.4, training=mode == tf.estimator.ModeKeys.TRAIN)

  # Logits layer
  # Input Tensor Shape: [batch_size, 1024]
  # Output Tensor Shape: [batch_size, 10]
  logits = tf.layers.dense(inputs=dropout, units=10)

  predictions = {
      # Generate predictions (for PREDICT and EVAL mode)
      "classes": tf.argmax(input=logits, axis=1),
      # Add `softmax_tensor` to the graph. It is used for PREDICT and by the
      # `logging_hook`.
      "probabilities": tf.nn.softmax(logits, name="softmax_tensor")
  }
  if mode == tf.estimator.ModeKeys.PREDICT:
    return tf.estimator.EstimatorSpec(mode=mode, predictions=predictions)

  # Calculate Loss (for both TRAIN and EVAL modes)
  onehot_labels = tf.one_hot(indices=tf.cast(labels, tf.int32), depth=10)
  loss = tf.losses.softmax_cross_entropy(
      onehot_labels=onehot_labels, logits=logits)

  # Configure the Training Op (for TRAIN mode)
  if mode == tf.estimator.ModeKeys.TRAIN:
    optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.001)
    train_op = optimizer.minimize(
        loss=loss,
        global_step=tf.train.get_global_step())
    return tf.estimator.EstimatorSpec(mode=mode, loss=loss, train_op=train_op)

  # Add evaluation metrics (for EVAL mode)
  eval_metric_ops = {
      "accuracy": tf.metrics.accuracy(
          labels=labels, predictions=predictions["classes"])}
  return tf.estimator.EstimatorSpec(
      mode=mode, loss=loss, eval_metric_ops=eval_metric_ops)


def main(unused_argv):
  # Load training and eval data
  mnist = tf.contrib.learn.datasets.load_dataset("mnist")
  train_data = mnist.train.images  # Returns np.array
  train_labels = np.asarray(mnist.train.labels, dtype=np.int32)
  eval_data = mnist.test.images  # Returns np.array
  eval_labels = np.asarray(mnist.test.labels, dtype=np.int32)

  # Create the Estimator
  mnist_classifier = tf.estimator.Estimator(
      model_fn=cnn_model_fn, model_dir="/tmp/mnist_convnet_model")

  # Set up logging for predictions
  # Log the values in the "Softmax" tensor with label "probabilities"
  tensors_to_log = {"probabilities": "softmax_tensor"}
  logging_hook = tf.train.LoggingTensorHook(
      tensors=tensors_to_log, every_n_iter=50)

  # Train the model
  train_input_fn = tf.estimator.inputs.numpy_input_fn(
      x={"x": train_data},
      y=train_labels,
      batch_size=100,
      num_epochs=None,
      shuffle=True)
  mnist_classifier.train(
      input_fn=train_input_fn,
      steps=20000,
      hooks=[logging_hook])

  # Evaluate the model and print results
  eval_input_fn = tf.estimator.inputs.numpy_input_fn(
      x={"x": eval_data},
      y=eval_labels,
      num_epochs=1,
      shuffle=False)
  eval_results = mnist_classifier.evaluate(input_fn=eval_input_fn)
  print(eval_results)


if __name__ == "__main__":
  tf.app.run()

＆＃13;

这是我得到的错误：

＆＃13;

ValueError: Dimension size must be evenly divisible by 3136 but is 49000 for 'Reshape_1' (op: 'Reshape') with input shapes: [100,7,7,10], [2] and with input tensors computed as partial shapes: input[1] = [?,3136].

＆＃13;

我想有人指出我需要在代码中更改以运行程序。谢谢！

Answer 1

这很简单。您更改了过滤器映射，因此您还需要采用[-180, -135, -90, -45, 0, 45, 90, 135, 180]，因为这会使卷积层变平以将其与密集层连接。在你的情况下，

reshape

所以你需要在这里改变这行代码，

Conv_1 28, 28, 1 -> 28, 28, 10
Pool_1 28, 28, 10 -> 14, 14, 10
Conv_2 14, 14, 10 -> 14, 14, 10
Pool_2 14, 14, 10 -> 7, 7, 10
Flatten-> FC Layer 7, 7, 10 = 7 * 7 * 10 = 490 -> 1024

卷积网络错误; Tensorflow - 值错误

1 个答案: