CNNの学習でエラーが発生しました。解決方法をご教授頂きたいです。

Question

CNNを学習させ、胸部X線の疾患を検出するプログラムを書いています。
現在は練習として少ない画像で練習しています。そのため、細菌に感染した肺とウイルスに感染した肺の画像で判別を行っております。

自分のGoogle driveに保存してある画像をリサイズし、CNNに読み込ませています。
CNNのモデルを学習させていましたが、下記のエラーが出てきます。

ValueError: in user code:

    File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 878, in train_function  *
        return step_function(self, iterator)
    File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 867, in step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 860, in run_step  **
        outputs = model.train_step(data)
    File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 810, in train_step
        y, y_pred, sample_weight, regularization_losses=self.losses)
    File "/usr/local/lib/python3.7/dist-packages/keras/engine/compile_utils.py", line 201, in __call__
        loss_value = loss_obj(y_t, y_p, sample_weight=sw)
    File "/usr/local/lib/python3.7/dist-packages/keras/losses.py", line 141, in __call__
        losses = call_fn(y_true, y_pred)
    File "/usr/local/lib/python3.7/dist-packages/keras/losses.py", line 245, in call  **
        return ag_fn(y_true, y_pred, **self._fn_kwargs)
    File "/usr/local/lib/python3.7/dist-packages/keras/losses.py", line 1665, in categorical_crossentropy
        y_true, y_pred, from_logits=from_logits, axis=axis)
    File "/usr/local/lib/python3.7/dist-packages/keras/backend.py", line 4994, in categorical_crossentropy
        target.shape.assert_is_compatible_with(output.shape)

    ValueError: Shapes (None, 1) and (None, 2) are incompatible

ソースコードはこちらになります。

from keras.utils import np_utils
from keras.models import Sequential
from keras.layers.convolutional import MaxPooling2D
from keras.layers import Activation, Conv2D, Flatten, Dense, Dropout
from keras.engine import base_layer_utils
from sklearn.model_selection import train_test_split
import numpy as np
import keras
import glob
import os
import cv2
!pip install tensorflow
!pip install tensorflow-gpu
!pip install keras

num_classes = 2

bacteria = []
virus = []

files = glob.glob("/content/drive/MyDrive/resize/bacteria_small/*.*")
i = 1
for file in files:
  img_bacteria = cv2.imread(file)
  img_bacteria = np.array(img_bacteria)
  bacteria.append(img_bacteria)
bacteria = np.array(bacteria)

files = glob.glob("/content/drive/MyDrive/resize/virus_small/*.*")
i = 1
for file in files:
  img_virus = cv2.imread(file)
  img_virus = np.array(img_virus)
  virus.append(img_virus)
virus = np.array(virus)

np.savez('gazou_np', bacteria, virus)

a = np.load('/content/gazou_np.npz')

x = np.concatenate([a['arr_0'],a['arr_1']])
bacteria_label = np.array([0]*len(a['arr_0']))
virus_label = np.array([1]*len(a['arr_1']))
y = np.concatenate([bacteria_label, virus_label])
y = np.array(y)

x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.20)


x_train = x_train.astype('float32')/255
x_test = x_test.astype('float32')/255

input_shape = x_train.shape

model = Sequential()

model.add(Conv2D(32, (3, 3), padding='same', input_shape = (input_shape)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))

model.add(Conv2D(64, (3, 3), padding='same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))

model.add(Conv2D(128, (3, 3), padding='same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))

model.add(Flatten())
model.add(Dense1(16))
model.add(Activation('relu'))
model.add(Dense2(64))
model.add(Activation('relu'))
model.add(Dense3(128))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))

model.summary()

model.compile(loss='categorical_crossentropy',
              optimizer='Adam',
              metrics=['accuracy'])


history = model.fit(x_train, y_train, epochs=50, validation_data=(x_test,y_test))

model.summary()の実行結果です。

Model: "sequential_1"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 conv2d_3 (Conv2D)           (None, 64, 64, 32)        896       
                                                                 
 activation_3 (Activation)   (None, 64, 64, 32)        0         
                                                                 
 max_pooling2d_3 (MaxPooling  (None, 32, 32, 32)       0         
 2D)                                                             
                                                                 
 dropout_3 (Dropout)         (None, 32, 32, 32)        0         
                                                                 
 conv2d_4 (Conv2D)           (None, 32, 32, 64)        18496     
                                                                 
 activation_4 (Activation)   (None, 32, 32, 64)        0         
                                                                 
 max_pooling2d_4 (MaxPooling  (None, 16, 16, 64)       0         
 2D)                                                             
                                                                 
 dropout_4 (Dropout)         (None, 16, 16, 64)        0         
                                                                 
 conv2d_5 (Conv2D)           (None, 16, 16, 128)       73856     
                                                                 
 activation_5 (Activation)   (None, 16, 16, 128)       0         
                                                                 
 max_pooling2d_5 (MaxPooling  (None, 8, 8, 128)        0         
 2D)                                                             
                                                                 
 dropout_5 (Dropout)         (None, 8, 8, 128)         0         
                                                                 
 flatten_1 (Flatten)         (None, 8192)              0         
                                                                 
 dense (Dense)               (None, 16)                131088    
                                                                 
 activation_6 (Activation)   (None, 16)                0         
                                                                 
 dense_1 (Dense)             (None, 64)                1088      
                                                                 
 activation_7 (Activation)   (None, 64)                0         
                                                                 
 dense_2 (Dense)             (None, 128)               8320      
                                                                 
 activation_8 (Activation)   (None, 128)               0         
                                                                 
 dropout_6 (Dropout)         (None, 128)               0         
                                                                 
 dense_3 (Dense)             (None, 2)                 258       
                                                                 
=================================================================
Total params: 234,002
Trainable params: 234,002
Non-trainable params: 0
_________________________________________________________________

なぜエラーが出てくるのかがわかりません。どなたか解決方法を教えてください。
よろしくお願いします。

Answer 1

出力層の期待するラベルの形状 (バッチサイズ, 2)
実際に与えられたラベルの形状 (バッチサイズ, 1)

で一致していないというエラーです。
ラベルを Ont-Hot 表現に変換してから、モデルに与えてください。
Keras だと to_categorical() を使うと変換できます。

Numpyユーティリティ - Keras Documentation

例: [A, A, B, B, B] -> [[1, 0], [1, 0], [0, 1], [0, 1], [0, 1]]

Comments

[fairlady]

実行できました。ありがとうございます。