質問編集履歴

コードの修正

2019/05/12 13:13

投稿

SuzuAya

スコア71

title CHANGED Viewed

File without changes

body CHANGED Viewed

@@ -128,12 +128,12 @@
 #original dataset
 #train
 filenames = glob.glob("./train/NORMAL_train_dataset/*.jpeg")
-x_train = []
+X = []
 for filename in filenames:
     img = img_to_array(load_img(
     filename, color_mode = "grayscale", target_size=(512,496))
-    x_train.append(img)
+    X.append(img)
 x_train = np.asarray(X)

全コード掲載

2019/05/12 13:13

投稿

SuzuAya

スコア71

title CHANGED Viewed

File without changes

body CHANGED Viewed

@@ -48,21 +48,239 @@
 import cv2
 import easydict
 from PIL import Image
+#from google.colab.patches import cv2_imshow
+import warnings
+warnings.filterwarnings('ignore')
+%matplotlib inline
+def sampling(args):
+    z_mean, z_log_var = args
+    batch = K.shape(z_mean)[0]
+    dim = K.int_shape(z_mean)[1]
+    # by default, random_normal has mean=0 and std=1.0
+    epsilon = K.random_normal(shape=(batch, dim))
+    return z_mean + K.exp(0.5 * z_log_var) * epsilon
+#def plot_results(models,
+                 #data,
+                 #batch_size=500,#128,
+                 #model_name="vae_OCT"):
+    """Plots labels and MNIST digits as function of 2-dim latent vector
+    # Arguments
+        models (tuple): encoder and decoder models
+        data (tuple): test data and label
+        batch_size (int): prediction batch size
+    encoder, decoder = models
+    x_test = data #, y_test削除
+    os.makedirs(model_name, exist_ok=True)
+        model_name (string): which model is using this function
+    """
+    filename = os.path.join('.', "vae_mean.png")
+    # display a 2D plot of the digit classes in the latent space
+    z_mean, _, _ = encoder.predict(x_test,
+                                   batch_size=batch_size)
+    #plt.figure(figsize=(12, 10))
+    #plt.scatter(z_mean[:, 0], z_mean[:, 1])#c=y_test削除
+    #plt.colorbar()
+    #plt.xlabel("z[0]")
+    #plt.ylabel("z[1]")
+    #plt.savefig(filename)
+    #plt.show()
+    #filename = os.path.join(model_name, "digits_over_latent.png")
+    # display a 30x30 2D manifold of digits
+    #n = 30
+    #digit_size = 496 うまく動かないので一旦プロット部分はすべてコメントアウト
+    #digit_size_width = 512 #width追加
+    #digit_size_height = 496 #height追加
+    #figure = np.zeros((digit_size_width * n, digit_size_height * n))#width, height追加
+    # linearly spaced coordinates corresponding to the 2D plot
+    # of digit classes in the latent space
+    #grid_x = np.linspace(-4, 4, n)
+    #grid_y = np.linspace(-4, 4, n)[::-1]
+    #for i, yi in enumerate(grid_y):
+        #for j, xi in enumerate(grid_x):
+            #z_sample = np.array([[xi, yi]])
+            #x_decoded = decoder.predict(z_sample)
+            #digit = x_decoded[0].reshape(digit_size_width, digit_size_height)#width, height追加
+            #figure[i * digit_size_width: (i + 1) * digit_size_height,#width, height追加
+                   #j * digit_size_width: (j + 1) * digit_size_height] = digit#width, height追加
+    #plt.figure(figsize=(10, 10))
+    #start_range = digit_size // 2
+    #end_range = n * digit_size + start_range + 1
+    #pixel_range = np.arange(start_range, end_range, digit_size)
+    #sample_range_x = np.round(grid_x, 1)
+    #sample_range_y = np.round(grid_y, 1)
+    #plt.xticks(pixel_range, sample_range_x)
+    #plt.yticks(pixel_range, sample_range_y)
+    #plt.xlabel("z[0]")
+    #plt.ylabel("z[1]")
+    #plt.imshow(figure, cmap='Greys_r')
+    #plt.savefig(filename)
+    #plt.show()
 #original dataset
 #train
 filenames = glob.glob("./train/NORMAL_train_dataset/*.jpeg")
+x_train = []
+for filename in filenames:
-X = []
+    img = img_to_array(load_img(
+    filename, color_mode = "grayscale", target_size=(512,496))
+    x_train.append(img)
+x_train = np.asarray(X)
+#test
+filenames = glob.glob("./validation/*.jpeg")
+x_test = []
 for filename in filenames:
     img = img_to_array(load_img(
-    filename, color_mode = "grayscale"
+    filename, color_mode = "grayscale", target_size=(512,496))
-    , target_size=(512,496)))
-    X.append(img)
+    x_test.append(img)
+x_test = np.asarray(x_test)
+image_size = x_train.shape[1]
+original_dim = 512 * 496 *1 #3削除
+x_train = np.reshape(x_train, [-1, original_dim,1])# x_train = np.reshape(x_train, [-1, original_dim])
+x_test = np.reshape(x_test, [-1, original_dim,1])# x_test = np.reshape(x_test, [-1, original_dim])
+x_train = x_train.astype('float32') / 255
+x_test = x_test.astype('float32') / 255
+#train_generator = train_datagen.flow(x_train)#追記。generator作成
+#test_generator = test_datagen.flow(x_test)#追記。generator作成
+print(x_train.shape)
+print(x_test.shape)
+# network parameters
+input_shape = (512, 496, 1)# (original_dim,)
+kernel_size = 3
+filters = 16
+#intermediate_dim = 512
+batch_size = 500#128
+latent_dim = 2# Dimensionality of the latent space: a plane 潜在空間の次元数：平面 https://fisproject.jp/2018/09/vae-with-python-keras/#vae-with-keras
+epochs = 5#1#50
+# build encoder model
+inputs = Input(shape=input_shape, name='encoder_input')
+x = inputs
+for i in range(4):
+    filters *= 2
+    x = Conv2D(filters=filters,kernel_size=kernel_size,activation='relu',strides=2,padding='same')(x)
+# shape info needed to build decoder model これは画像のshapeとって割る時とかに結構使う. ちなみにtensorflowでのみ動作します. https://www.mathgram.xyz/entry/keras/backend
+shape = K.int_shape(x)
+# use reparameterization trick to push the sampling out as input
+# note that "output_shape" isn't necessary with the TensorFlow backend
+z = Lambda(sampling, output_shape=(latent_dim,), name='z')([z_mean, z_log_var])
+# instantiate encoder model
+encoder = Model(inputs, [z_mean, z_log_var, z], name='encoder')
+encoder.summary()
+plot_model(encoder, to_file='vae_mlp_encoder.png', show_shapes=True)
+# build decoder model
+latent_inputs = Input(shape=(latent_dim,), name='z_sampling')
+x = Dense(shape[1] * shape[2] * shape[3], activation='relu')(latent_inputs)
+x = Reshape((shape[1], shape[2], shape[3]))(x)
+for i in range(4):
+    x = Conv2DTranspose(filters=filters, kernel_size=kernel_size, activation='relu', strides=2, padding='same')(x)
+    filters //= 2
+outputs = Conv2DTranspose(filters=1, kernel_size=kernel_size, activation='sigmoid', padding='same', name='decoder_output')(x)
+# instantiate decoder model
+decoder = Model(latent_inputs, outputs, name='decoder')
+decoder.summary()
+plot_model(decoder, to_file='vae_mlp_decoder.png', show_shapes=True)
+# instantiate VAE model
+outputs = decoder(encoder(inputs)[2])
+vae = Model(inputs, outputs, name='vae_mlp')
+if __name__ == '__main__':
+    args = easydict.EasyDict({
+   "batchsize": 500,#40,
+    "epoch": 1,#50,
+    #"gpu": 0,
+    "out": "result",
+    "resume": False,
+    #"unit": 1000
+})
+    #parser = argparse.ArgumentParser() parserがうまくうごかないため削除
+    #help_ = "Load h5 model trained weights"
+    #parser.add_argument("-w", "--weights", help=help_)
+    #help_ = "Use mse loss instead of binary cross entropy (default)"
+    #parser.add_argument("-m",
+                        #"--mse",
+                        #help=help_, action='store_true')
+    #args = parser.parse_args()
+    models = (encoder, decoder)
+    data = (x_test)#, y_test削除
+    # VAE loss = mse_loss or xent_loss + kl_loss
+    #if args.mse:
+        #reconstruction_loss = mse(inputs, outputs)
+    #else:
+    reconstruction_loss = binary_crossentropy(inputs,
+                                                  outputs)
+    reconstruction_loss *= original_dim
+    kl_loss = 1 + z_log_var - K.square(z_mean) - K.exp(z_log_var)
+    kl_loss = K.sum(kl_loss, axis=-1)
+    kl_loss *= -0.5
+    vae_loss = K.mean(reconstruction_loss + kl_loss)
+    vae.add_loss(vae_loss)
+    vae.compile(optimizer='adam')
+    vae.summary()
+    plot_model(vae,
+    to_file='vae_mlp.png',
+    show_shapes=True)
+    callbacks = []
+    callbacks.append(ModelCheckpoint(filepath="model.ep{epoch:02d}.h5"))# 各epochでのモデルの保存
+    callbacks.append(EarlyStopping(monitor='val_loss', patience=0, verbose=1))
+    callbacks.append(LearningRateScheduler(lambda ep: float(1e-3 / 3 ** (ep * 4 // MAX_EPOCH))))
+    callbacks.append(CSVLogger("history.csv"))
+    #if args.weights:
+        #vae.load_weights(args.weights)
+    #else:
+        # train the autoencoder
+    history = vae.fit(x_train,
+                epochs=epochs,
+                batch_size=batch_size,
+                validation_data=(x_test, None),
+                callbacks=callbacks)
+    score = model.evaluate(x_test, verbose=0)#y_test削除
+    print('Test loss:', score[0])
+    print('Test accuracy:', score[1])
+    plt.plot(history.history["acc"], label="acc", ls="-", marker="o")
+    plt.plot(history.history["val_acc"], label="val_acc", ls="-", marker="x")
-x_train = np.asarray(X)
+    plt.ylabel("accuracy")
+    plt.xlabel("epoch")
+    plt.legend(loc="best")
+    plt.show()
 ```

コードの修正

2019/05/12 13:11

投稿

SuzuAya

スコア71

title CHANGED Viewed

File without changes

body CHANGED Viewed

@@ -53,16 +53,16 @@
 #train
 filenames = glob.glob("./train/NORMAL_train_dataset/*.jpeg")
-x_train = []
+X = []
 for filename in filenames:
     img = img_to_array(load_img(
     filename, color_mode = "grayscale"
     , target_size=(512,496)))
-    x_train.append(img)
+    X.append(img)
-x_train = np.asarray(x_train)
+x_train = np.asarray(X)
 ```