編集履歴

質問編集履歴

コードを載せました

2019/01/17 05:32

投稿

oriharas

スコア12

test CHANGED Viewed

File without changes

test CHANGED Viewed

@@ -1,3 +1,451 @@
-現在autoencoderに画像を入力し、autoencoderから出力された画像で教師データどうかの判定を行うといったGANの開発を行なっています。
+現在autoencoderに画像を入力し、autoencoderから出力された画像で教師データどうかの判定を行いautoencoderを学習させるといったGANの開発を行なっています。
+標準のGANならばランダムノイズから画像生成するコードの部分の改良を行なったため、エラーが起こってるのではないかと思います。
 しかし実行しようとすると以下のようなエラーが発生しています。
+```
+Traceback (most recent call last):
+  File "keras_dcgan_copy.py", line 192, in <module>
+    main()
+  File "keras_dcgan_copy.py", line 150, in main
+    discriminator_on_generator = generator_containing_discriminator(generator, discriminator)
+  File "keras_dcgan_copy.py", line 107, in generator_containing_discriminator
+    model.add(discriminator)
+  File "/usr/local/lib/python3.6/dist-packages/keras/engine/sequential.py", line 181, in add
+    output_tensor = layer(self.outputs[0])
+  File "/usr/local/lib/python3.6/dist-packages/keras/engine/base_layer.py", line 457, in __call__
+    output = self.call(inputs, **kwargs)
+  File "/usr/local/lib/python3.6/dist-packages/keras/engine/network.py", line 564, in call
+    output_tensors, _, _ = self.run_internal_graph(inputs, masks)
+  File "/usr/local/lib/python3.6/dist-packages/keras/engine/network.py", line 721, in run_internal_graph
+    layer.call(computed_tensor, **kwargs))
+  File "/usr/local/lib/python3.6/dist-packages/keras/layers/convolutional.py", line 171, in call
+    dilation_rate=self.dilation_rate)
+  File "/usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py", line 3650, in conv2d
+    data_format=tf_data_format)
+  File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/nn_ops.py", line 779, in convolution
+    data_format=data_format)
+  File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/nn_ops.py", line 839, in __init__
+    filter_shape[num_spatial_dims]))
+ValueError: number of input channels does not match corresponding dimension of filter, 32 != 3
+```
+機械学習初心者で汚いコードかもしれませんが、ご教授お願いします。
+以上がコードの全文です
+```python　Keras
+from keras.models import Sequential
+from keras.layers import Dense
+from keras.layers import Reshape
+from keras.layers.core import Activation
+from keras.layers.normalization import BatchNormalization
+from keras.layers.convolutional import UpSampling2D
+from keras.layers.convolutional import Conv2D, MaxPooling2D
+from keras.layers.advanced_activations import LeakyReLU
+from keras.layers.core import Flatten,Dropout
+from keras.optimizers import Adam
+import numpy as np
+from PIL import Image
+import os
+import glob
+import random
+n_colors = 3
+'''
+def generator_model():
+    model = Sequential()
+    model.add(Dense(1024, input_shape=(100,)))
+    model.add(Activation('tanh'))
+    model.add(Dense(128 * 16 * 16))
+    model.add(BatchNormalization())
+    model.add(Activation('tanh'))
+    model.add(Reshape((16, 16, 128)))
+    model.add(UpSampling2D(size=(2, 2)))
+    model.add(Conv2D(64, (5, 5), padding='same'))
+    model.add(Activation('tanh'))
+    model.add(UpSampling2D(size=(2, 2)))
+    model.add(Conv2D(n_colors, (5, 5), padding='same'))
+    model.add(Activation('tanh'))
+    return model
+'''
+def generator_model():
+    model = Sequential()
+    #encode
+    model.add(Conv2D(32, (5, 5),input_shape=(64, 64, n_colors),activation='relu', padding='same'))
+    model.add(MaxPooling2D(pool_size=(2, 2),padding='same'))
+    model.add(Conv2D(16, (5, 5),activation='relu', padding='same'))
+    model.add(MaxPooling2D(pool_size=(2, 2),padding='same'))
+    model.add(Conv2D(16, (5, 5),activation='relu', padding='same'))
+    model.add(MaxPooling2D(pool_size=(2, 2),padding='same'))
+    #decode
+    model.add(Conv2D(16,(5,5),activation='relu',padding='same'))
+    model.add(UpSampling2D(size=(2, 2)))
+    model.add(Conv2D(16,(5,5),activation='relu',padding='same'))
+    model.add(UpSampling2D(size=(2, 2)))
+    model.add(Conv2D(32,(5,5),activation='relu'))
+    model.add(UpSampling2D(size=(2, 2)))
+    return model
+def discriminator_model():
+    model = Sequential()
+    model.add(Conv2D(64, (5, 5), input_shape=(64, 64, n_colors), padding='same'))
+    model.add(LeakyReLU(alpha=0.2))
+    model.add(MaxPooling2D(pool_size=(2, 2)))
+    model.add(Conv2D(128, (5, 5)))
+    model.add(LeakyReLU(alpha=0.2))
+    model.add(MaxPooling2D(pool_size=(2, 2)))
+    model.add(Flatten())
+    model.add(Dense(1024))
+    model.add(LeakyReLU(alpha=0.2))
+    model.add(Dense(1))
+    model.add(Activation('sigmoid'))
+    return model
+'''
+def discriminator_model():
+    model = Sequential()
+    model.add(Conv2D(64, (5,5), strides=(2, 2), input_shape=(64, 64, 3), padding="same"))
+    model.add(LeakyReLU(0.2))
+    model.add(Conv2D(128, (5,5), strides=(2, 2)))
+    model.add(LeakyReLU(0.2))
+    model.add(Flatten())
+    model.add(Dense(256))
+    model.add(LeakyReLU(0.2))
+    model.add(Dropout(0.5))
+    model.add(Dense(1))
+    model.add(Activation('sigmoid'))
+    return model
+'''
+def generator_containing_discriminator(generator, discriminator):
+    model = Sequential()
+    model.add(generator)
+    model.add(discriminator)
+    return model
+def image_batch(batch_size):
+    files = glob.glob("./in_images/**/*.jpg", recursive=True)
+    files = random.sample(files, batch_size)
+    # print(files)
+    res = []
+    for path in files:
+        img = Image.open(path)
+        img = img.resize((64, 64))
+        arr = np.array(img)
+        arr = (arr - 127.5) / 127.5
+        arr.resize((64, 64, n_colors))
+        res.append(arr)
+    return np.array(res)
+def combine_images(generated_images, cols=5, rows=5):
+    shape = generated_images.shape
+    h = shape[1]
+    w = shape[2]
+    image = np.zeros((rows * h,  cols * w, n_colors))
+    for index, img in enumerate(generated_images):
+        if index >= cols * rows:
+            break
+        i = index // cols
+        j = index % cols
+        image[i*h:(i+1)*h, j*w:(j+1)*w, :] = img[:, :, :]
+    image = image * 127.5 + 127.5
+    image = Image.fromarray(image.astype(np.uint8))
+    return image
+def set_trainable(model, trainable):
+    model.trainable = trainable
+    for layer in model.layers:
+        layer.trainable = trainable
+def main():
+    batch_size = 64
+    discriminator = discriminator_model()
+    generator = generator_model()
+    discriminator_on_generator = generator_containing_discriminator(generator, discriminator)
+    set_trainable(discriminator, False)
+    discriminator_on_generator.compile(loss='binary_crossentropy', optimizer=Adam(lr=0.0002, beta_1=0.5))
+    print(generator.summary())
+    print(discriminator_on_generator.summary())
+    set_trainable(discriminator, True)
+    discriminator.compile(loss='binary_crossentropy', optimizer=Adam(lr=0.0002, beta_1=0.5))
+    print(discriminator.summary())
+    for i in range(30 * 1000):
+        batch_images = image_batch(batch_size)
+        # generator更新
+        noise = np.random.uniform(size=[batch_size, batch_images], low=-1.0, high=1.0)
+        generated_images = generator.predict(image_batch)
+        # discriminatorを更新
+        X = np.concatenate((batch_images, generated_images))
+        # 訓練データのラベルが1、生成画像のラベルが0になるよう学習する
+        y = [1] * batch_size + [0] * batch_size
+        d_loss = discriminator.train_on_batch(X, y)
+        # generator更新
+        noise = np.random.uniform(size=[batch_size, batch_images], low=-1.0, high=1.0)
+        # 生成画像をdiscriminatorにいれたときに
+        # 出力が1に近くなる(訓練画像と識別される確率が高くなる)ように学習する
+        g_loss = discriminator_on_generator.train_on_batch(noise, [1] * batch_size)
+        if i % 100 == 0:
+            print("step %d d_loss, g_loss : %g %g" % (i, d_loss, g_loss))
+            image = combine_images(generated_images)
+            os.system('mkdir -p ./gen_images')
+            image.save("./gen_images/gen%05d.jpg" % i)
+            generator.save_weights('generator.h5', True)
+            discriminator.save_weights('discriminator.h5', True)
+main()
+```