0

我正在尝试为灰度 MRI 数据的二进制分类构建 3D CNN。我是新手，所以不要打任何拳，我是来学习的！我有 20 个 3D 文件的子样本，尺寸为 (189、233、197)。我使用 np.reshape 添加 aa 维度作为通道来获得 (189, 233, 197, 1)。我使用 tf.shape 来获取数据集的形状，即

<tf.Tensor: shape=(5,), dtype=int32, numpy=array([ 20, 189, 233, 197,   1], dtype=int32)>

在标签数据上也是如此

<tf.Tensor: shape=(1,), dtype=int32, numpy=array([20], dtype=int32)>

以下是我正在使用的完整代码：

import numpy as np
import glob
import os
import tensorflow as tf
import pandas as pd
import glob

import SimpleITK as sitk

from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split

from tensorflow.keras.utils import plot_model
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from tensorflow.keras.layers import Dropout

from google.colab import drive
drive.mount('/content/gdrive')

datapath = ('/content/gdrive/My Drive/DirectoryTest/All Data/')
patients = os.listdir(datapath)
labels_df = pd.read_csv('/content/Data_Index.csv', index_col = 0 )

FullDataSet = []

for patient in patients:
  a = sitk.ReadImage(datapath + patient)
  b = sitk.GetArrayFromImage(a)
  c = np.reshape(b, (189,233,197))
  FullDataSet.append(c)

labelset = []

for i in patients:
  label = labels_df.loc[i, 'Group']
  if label == 'AD':  # use `==` instead of `is` to compare strings
    labelset.append(0.)
  elif label == 'CN':
    labelset.append(1.)
  else:
      raise "Oops, unknown label" 

labelset = np.array(labelset)

x_train, x_valid, y_train, y_valid = train_test_split(FullDataSet, labelset, train_size=0.75)

## 3D CNN

CNN_model = tf.keras.Sequential(
  [
      #tf.keras.layers.Reshape([189, 233, 197, 1], input_shape=[189, 233, 197]), 
      tf.keras.layers.Input(shape =[ 189, 233, 197, 1] ),                       
      tf.keras.layers.Conv3D(kernel_size=(7, 7, 7), filters=32, activation='relu',
                          padding='same', strides=(3, 3, 3)),
      #tf.keras.layers.BatchNormalization(),
      tf.keras.layers.MaxPool3D(pool_size=(3, 3, 3), padding='same'),
      tf.keras.layers.Dropout(0.20),
      
      tf.keras.layers.Conv3D(kernel_size=(5, 5, 5), filters=64, activation='relu',
                          padding='same', strides=(3, 3, 3)),
      #tf.keras.layers.BatchNormalization(),
      tf.keras.layers.MaxPool3D(pool_size=(2, 2, 2), padding='same'),
      tf.keras.layers.Dropout(0.20),

      tf.keras.layers.Conv3D(kernel_size=(3, 3, 3), filters=128, activation='relu',
                          padding='same', strides=(1, 1, 1)),
      #tf.keras.layers.BatchNormalization(),
      tf.keras.layers.MaxPool3D(pool_size=(2, 2, 2), padding='same'),
      tf.keras.layers.Dropout(0.20), 

      # last activation could be either sigmoid or softmax, need to look into this more. Sig for binary output, Soft for multi output 
      tf.keras.layers.Flatten(),
      tf.keras.layers.Dense(256, activation='relu'),   
      tf.keras.layers.Dense(64, activation='relu'),
      tf.keras.layers.Dropout(0.20),
      tf.keras.layers.Dense(1, activation='sigmoid')

  ])
# Compile the model
CNN_model.compile(optimizer=tf.keras.optimizers.Adam(lr=0.00001), loss='binary_crossentropy', metrics=['accuracy'])

# print model layers
CNN_model.summary()

CNN_history = CNN_model.fit(x_train, y_train, epochs=10, validation_data=[x_valid, y_valid])

当我尝试拟合模型时，维度似乎没有对齐，并且出现以下错误：

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-48-c698c45a4d36> in <module>()
      1 #running of the model
      2 #CNN_history = CNN_model.fit(dataset_train, epochs=100, validation_data =dataset_test, validation_steps=1)
----> 3 CNN_history = CNN_model.fit(x_train, y_train, epochs=10, validation_data=[x_valid, y_valid], batch_size = 1)
      4 
      5 

3 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py in _method_wrapper(self, *args, **kwargs)
    106   def _method_wrapper(self, *args, **kwargs):
    107     if not self._in_multi_worker_mode():  # pylint: disable=protected-access
--> 108       return method(self, *args, **kwargs)
    109 
    110     # Running inside `run_distribute_coordinator` already.

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)
   1061           use_multiprocessing=use_multiprocessing,
   1062           model=self,
-> 1063           steps_per_execution=self._steps_per_execution)
   1064 
   1065       # Container that configures and calls `tf.keras.Callback`s.

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/data_adapter.py in __init__(self, x, y, sample_weight, batch_size, steps_per_epoch, initial_epoch, epochs, shuffle, class_weight, max_queue_size, workers, use_multiprocessing, model, steps_per_execution)
   1115         use_multiprocessing=use_multiprocessing,
   1116         distribution_strategy=ds_context.get_strategy(),
-> 1117         model=model)
   1118 
   1119     strategy = ds_context.get_strategy()

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/data_adapter.py in __init__(self, x, y, sample_weights, sample_weight_modes, batch_size, epochs, steps, shuffle, **kwargs)
    280             label, ", ".join(str(i.shape[0]) for i in nest.flatten(data)))
    281       msg += "Please provide data which shares the same first dimension."
--> 282       raise ValueError(msg)
    283     num_samples = num_samples.pop()
    284 

ValueError: Data cardinality is ambiguous:
  x sizes: 189, 189, 189, 189, 189, 189, 189, 189, 189, 189, 189, 189, 189, 189, 189
  y sizes: 15
Please provide data which shares the same first dimension.

训练拆分设置为 0.75，因此 20 个中有 15 个。我很困惑为什么这不起作用并且无法弄清楚为什么这是模型正在接收的输入。我之前得到了一些帮助，使用以下代码创建一个虚拟集会导致模型运行：

train_size = 20
val_size = 5

X_train = np.random.random([train_size, 189, 233, 197]).astype(np.float32)
X_valid = np.random.random([val_size, 189, 233, 197]).astype(np.float32)
y_train = np.random.randint(2, size=train_size).astype(np.float32)
y_valid = np.random.randint(2, size=val_size).astype(np.float32)

在这个问题上，我已经把头撞在墙上一段时间了。任何帮助将不胜感激。

4

1 回答 1

0

我目前没有评论权限，否则我会，因为这可能不是一个完整的答案，所以我会说：

当我尝试创建一个玩具 4 维数据集，然后将其附加到一个列表中（添加一个通道 - 我相信你已经这样做了？），我得到的形状不是（dim1，dim2，dim3，dim4，通道）但是（通道，dim1，dim2，dim3，dim4）。我在下面包含了一个工作示例：

import numpy as np

df = np.arange(0,625).reshape(5,5,5,5)
print(df.shape) # returns (5,5,5,5)

lst = []
lst.append(df)

print(np.asarray(g).shape) # returns (1,5,5,5,5)

基于此，您的数据形状可能实际上是 (1, 189, 233, 197) 而不是 (189, 233, 197, 1) 吗？

此外，给我的错误消息似乎暗示您没有为 X 和 y 传递相同数量的样本？

ValueError: Data cardinality is ambiguous:
  x sizes: 189, 189, 189, 189, 189, 189, 189, 189, 189, 189, 189, 189, 189, 189, 189
  y sizes: 15
Please provide data which shares the same first dimension.

通常，网络的输入将具有相同的第一个大小（并以窃取您自己的玩具数据集为例，然后运行）：

print(X_train.shape, y_train_shape, X_test.shape, y_test.shape)
# returns: (20, 189, 233, 197), (20,) (5, 189, 233, 197) (5,)

它们匹配是因为这本质上意味着每个样本对应一个标签，反之亦然。在我看来，错误消息似乎是在说明 X 和 y 输入的每个维度的第一个维度分别为 189 和 15。您可以在输入网络之前立即仔细检查形状吗？

于 2020-08-14T13:43:31.440 回答