Python keras.layers.Flatten() Examples

def ann_model(input_shape):

    inp = Input(shape=input_shape, name='mfcc_in')
    model = inp

    model = Conv1D(filters=12, kernel_size=(3), activation='relu')(model)
    model = Conv1D(filters=12, kernel_size=(3), activation='relu')(model)
    model = Flatten()(model)

    model = Dense(56)(model)
    model = Activation('relu')(model)
    model = BatchNormalization()(model)
    model = Dropout(0.2)(model)
    model = Dense(28)(model)
    model = Activation('relu')(model)
    model = BatchNormalization()(model)

    model = Dense(1)(model)
    model = Activation('sigmoid')(model)

    model = Model(inp, model)
    return model 

def build_discriminator(self):

        model = Sequential()

        model.add(Conv2D(64, kernel_size=3, strides=2, input_shape=self.missing_shape, padding="same"))
        model.add(LeakyReLU(alpha=0.2))
        model.add(BatchNormalization(momentum=0.8))
        model.add(Conv2D(128, kernel_size=3, strides=2, padding="same"))
        model.add(LeakyReLU(alpha=0.2))
        model.add(BatchNormalization(momentum=0.8))
        model.add(Conv2D(256, kernel_size=3, padding="same"))
        model.add(LeakyReLU(alpha=0.2))
        model.add(BatchNormalization(momentum=0.8))
        model.add(Flatten())
        model.add(Dense(1, activation='sigmoid'))
        model.summary()

        img = Input(shape=self.missing_shape)
        validity = model(img)

        return Model(img, validity) 

def build_discriminators(self):

        img1 = Input(shape=self.img_shape)
        img2 = Input(shape=self.img_shape)

        # Shared discriminator layers
        model = Sequential()
        model.add(Flatten(input_shape=self.img_shape))
        model.add(Dense(512))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dense(256))
        model.add(LeakyReLU(alpha=0.2))

        img1_embedding = model(img1)
        img2_embedding = model(img2)

        # Discriminator 1
        validity1 = Dense(1, activation='sigmoid')(img1_embedding)
        # Discriminator 2
        validity2 = Dense(1, activation='sigmoid')(img2_embedding)

        return Model(img1, validity1), Model(img2, validity2) 

def build_model(self):
        input = Input(shape=self.state_size)
        conv = Conv2D(16, (8, 8), strides=(4, 4), activation='relu')(input)
        conv = Conv2D(32, (4, 4), strides=(2, 2), activation='relu')(conv)
        conv = Flatten()(conv)
        fc = Dense(256, activation='relu')(conv)
        policy = Dense(self.action_size, activation='softmax')(fc)
        value = Dense(1, activation='linear')(fc)

        actor = Model(inputs=input, outputs=policy)
        critic = Model(inputs=input, outputs=value)

        actor._make_predict_function()
        critic._make_predict_function()

        actor.summary()
        critic.summary()

        return actor, critic

    # make loss function for Policy Gradient
    # [log(action probability) * advantages] will be input for the back prop
    # we add entropy of action probability to loss 

def build_discriminator(self):

        img = Input(shape=self.img_shape)

        model = Sequential()
        model.add(Conv2D(64, kernel_size=4, strides=2, padding='same', input_shape=self.img_shape))
        model.add(LeakyReLU(alpha=0.8))
        model.add(Conv2D(128, kernel_size=4, strides=2, padding='same'))
        model.add(LeakyReLU(alpha=0.2))
        model.add(InstanceNormalization())
        model.add(Conv2D(256, kernel_size=4, strides=2, padding='same'))
        model.add(LeakyReLU(alpha=0.2))
        model.add(InstanceNormalization())

        model.summary()

        img = Input(shape=self.img_shape)
        features = model(img)

        validity = Conv2D(1, kernel_size=4, strides=1, padding='same')(features)

        label = Flatten()(features)
        label = Dense(self.num_classes+1, activation="softmax")(label)

        return Model(img, [validity, label]) 

def build_encoder(self):
        model = Sequential()

        model.add(Flatten(input_shape=self.img_shape))
        model.add(Dense(512))
        model.add(LeakyReLU(alpha=0.2))
        model.add(BatchNormalization(momentum=0.8))
        model.add(Dense(512))
        model.add(LeakyReLU(alpha=0.2))
        model.add(BatchNormalization(momentum=0.8))
        model.add(Dense(self.latent_dim))

        model.summary()

        img = Input(shape=self.img_shape)
        z = model(img)

        return Model(img, z) 

def build_discriminator(self):

        z = Input(shape=(self.latent_dim, ))
        img = Input(shape=self.img_shape)
        d_in = concatenate([z, Flatten()(img)])

        model = Dense(1024)(d_in)
        model = LeakyReLU(alpha=0.2)(model)
        model = Dropout(0.5)(model)
        model = Dense(1024)(model)
        model = LeakyReLU(alpha=0.2)(model)
        model = Dropout(0.5)(model)
        model = Dense(1024)(model)
        model = LeakyReLU(alpha=0.2)(model)
        model = Dropout(0.5)(model)
        validity = Dense(1, activation="sigmoid")(model)

        return Model([z, img], validity) 

def build_classifier(self):

        def clf_layer(layer_input, filters, f_size=4, normalization=True):
            """Classifier layer"""
            d = Conv2D(filters, kernel_size=f_size, strides=2, padding='same')(layer_input)
            d = LeakyReLU(alpha=0.2)(d)
            if normalization:
                d = InstanceNormalization()(d)
            return d

        img = Input(shape=self.img_shape)

        c1 = clf_layer(img, self.cf, normalization=False)
        c2 = clf_layer(c1, self.cf*2)
        c3 = clf_layer(c2, self.cf*4)
        c4 = clf_layer(c3, self.cf*8)
        c5 = clf_layer(c4, self.cf*8)

        class_pred = Dense(self.num_classes, activation='softmax')(Flatten()(c5))

        return Model(img, class_pred) 

def build_discriminator(self):

        model = Sequential()

        model.add(Flatten(input_shape=self.img_shape))
        model.add(Dense(512))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dense(256))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dense(1, activation='sigmoid'))
        model.summary()

        img = Input(shape=self.img_shape)
        validity = model(img)

        return Model(img, validity) 

def build_discriminator(self):

        model = Sequential()

        model.add(Flatten(input_shape=self.img_shape))
        model.add(Dense(512))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dense(256))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dense(1, activation='sigmoid'))
        model.summary()

        img = Input(shape=self.img_shape)
        validity = model(img)

        return Model(img, validity) 

def value_distribution_network(input_shape, num_atoms, action_size, learning_rate):
        """Model Value Distribution

        With States as inputs and output Probability Distributions for all Actions
        """

        state_input = Input(shape=(input_shape)) 
        cnn_feature = Convolution2D(32, 8, 8, subsample=(4,4), activation='relu')(state_input)
        cnn_feature = Convolution2D(64, 4, 4, subsample=(2,2), activation='relu')(cnn_feature)
        cnn_feature = Convolution2D(64, 3, 3, activation='relu')(cnn_feature)
        cnn_feature = Flatten()(cnn_feature)
        cnn_feature = Dense(512, activation='relu')(cnn_feature)

        distribution_list = []
        for i in range(action_size):
            distribution_list.append(Dense(num_atoms, activation='softmax')(cnn_feature))

        model = Model(input=state_input, output=distribution_list)

        adam = Adam(lr=learning_rate)
        model.compile(loss='categorical_crossentropy',optimizer=adam)

        return model 

def assda_feat_ext(main_input, l2_weight=0.0, small_model=False):
    padding = 'same'
    maxpool_strides = 2 if small_model else 1
    net = dnn.Convolution2D(32, (3, 3),padding=padding, activation='relu',
                                kernel_regularizer=dnn.keras.regularizers.l2(l2_weight))(main_input)
    net = dnn.Convolution2D(32, (3, 3), padding=padding, activation='relu',
                                kernel_regularizer=dnn.keras.regularizers.l2(l2_weight))(net)
    net = dnn.MaxPooling2D(pool_size=(2, 2), strides=maxpool_strides)(net)
    # net = dnn.Dropout(0.5)(net)
    net = dnn.Convolution2D(64, (3, 3), padding=padding, activation='relu',
                                kernel_regularizer=dnn.keras.regularizers.l2(l2_weight))(net)
    net = dnn.Convolution2D(64, (3, 3), padding=padding, activation='relu',
                                kernel_regularizer=dnn.keras.regularizers.l2(l2_weight))(net)
    net = dnn.MaxPooling2D(pool_size=(2, 2), strides=maxpool_strides)(net)
    # net = dnn.Dropout(0.5)(net)
    net = dnn.Convolution2D(128, (3, 3), padding=padding, activation='relu',
                                kernel_regularizer=dnn.keras.regularizers.l2(l2_weight))(net)
    net = dnn.Convolution2D(128, (3, 3), padding=padding, activation='relu',
                                kernel_regularizer=dnn.keras.regularizers.l2(l2_weight))(net)
    net = dnn.MaxPooling2D(pool_size=(2, 2), strides=maxpool_strides)(net)
#   
    net = dnn.Flatten()(net)
    net = dnn.Dense(128,activation='sigmoid',
                        kernel_regularizer=dnn.keras.regularizers.l2(l2_weight),name='feat_ext')(net)
    return net 

def encoder(self):

        if self.E:
            return self.E

        inp = Input(shape = [im_size, im_size, 3])

        x = d_block(inp, 1 * cha)   #64
        x = d_block(x, 2 * cha)   #32
        x = d_block(x, 3 * cha)   #16
        x = d_block(x, 4 * cha)  #8
        x = d_block(x, 8 * cha)  #4
        x = d_block(x, 16 * cha, p = False)  #4

        x = Flatten()(x)

        x = Dense(16 * cha, kernel_initializer = 'he_normal')(x)
        x = LeakyReLU(0.2)(x)

        x = Dense(latent_size, kernel_initializer = 'he_normal', bias_initializer = 'zeros')(x)

        self.E = Model(inputs = inp, outputs = x)

        return self.E 

def build_model(x_train, num_classes):
        # Reset default graph. Keras leaves old ops in the graph,
        # which are ignored for execution but clutter graph
        # visualization in TensorBoard.
        tf.reset_default_graph()

        inputs = KL.Input(shape=x_train.shape[1:], name="input_image")
        x = KL.Conv2D(32, (3, 3), activation='relu', padding="same",
                      name="conv1")(inputs)
        x = KL.Conv2D(64, (3, 3), activation='relu', padding="same",
                      name="conv2")(x)
        x = KL.MaxPooling2D(pool_size=(2, 2), name="pool1")(x)
        x = KL.Flatten(name="flat1")(x)
        x = KL.Dense(128, activation='relu', name="dense1")(x)
        x = KL.Dense(num_classes, activation='softmax', name="dense2")(x)

        return KM.Model(inputs, x, "digit_classifier_model")

    # Load MNIST Data 

def build_localmodel(self):
        input = Input(shape=self.state_size)
        conv = Conv2D(16, (8, 8), strides=(4, 4), activation='relu')(input)
        conv = Conv2D(32, (4, 4), strides=(2, 2), activation='relu')(conv)
        conv = Flatten()(conv)
        fc = Dense(256, activation='relu')(conv)
        policy = Dense(self.action_size, activation='softmax')(fc)
        value = Dense(1, activation='linear')(fc)

        actor = Model(inputs=input, outputs=policy)
        critic = Model(inputs=input, outputs=value)

        actor._make_predict_function()
        critic._make_predict_function()

        actor.set_weights(self.actor.get_weights())
        critic.set_weights(self.critic.get_weights())

        actor.summary()
        critic.summary()

        return actor, critic 

def __init__(self, model_path=None):
        if model_path is not None:
            self.model = self.load_model(model_path)
        else:
            # VGG16 last conv features
            inputs = Input(shape=(7, 7, 512))
            x = Convolution2D(128, 1, 1)(inputs)
            x = Flatten()(x)

            # Cls head
            h_cls = Dense(256, activation='relu', W_regularizer=l2(l=0.01))(x)
            h_cls = Dropout(p=0.5)(h_cls)
            cls_head = Dense(20, activation='softmax', name='cls')(h_cls)

            # Reg head
            h_reg = Dense(256, activation='relu', W_regularizer=l2(l=0.01))(x)
            h_reg = Dropout(p=0.5)(h_reg)
            reg_head = Dense(4, activation='linear', name='reg')(h_reg)

            # Joint model
            self.model = Model(input=inputs, output=[cls_head, reg_head]) 

def modelA():
    model = Sequential()
    model.add(Conv2D(64, (5, 5),
                            padding='valid'))
    model.add(Activation('relu'))

    model.add(Conv2D(64, (5, 5)))
    model.add(Activation('relu'))

    model.add(Dropout(0.25))

    model.add(Flatten())
    model.add(Dense(128))
    model.add(Activation('relu'))

    model.add(Dropout(0.5))
    model.add(Dense(FLAGS.NUM_CLASSES))
    return model 

def modelB():
    model = Sequential()
    model.add(Dropout(0.2, input_shape=(FLAGS.IMAGE_ROWS,
                                        FLAGS.IMAGE_COLS,
                                        FLAGS.NUM_CHANNELS)))
    model.add(Convolution2D(64, 8, 8,
                            subsample=(2, 2),
                            border_mode='same'))
    model.add(Activation('relu'))

    model.add(Convolution2D(128, 6, 6,
                            subsample=(2, 2),
                            border_mode='valid'))
    model.add(Activation('relu'))

    model.add(Convolution2D(128, 5, 5,
                            subsample=(1, 1)))
    model.add(Activation('relu'))

    model.add(Dropout(0.5))

    model.add(Flatten())
    model.add(Dense(FLAGS.NUM_CLASSES))
    return model 

def modelC():
    model = Sequential()
    model.add(Convolution2D(128, 3, 3,
                            border_mode='valid',
                            input_shape=(FLAGS.IMAGE_ROWS,
                                         FLAGS.IMAGE_COLS,
                                         FLAGS.NUM_CHANNELS)))
    model.add(Activation('relu'))

    model.add(Convolution2D(64, 3, 3))
    model.add(Activation('relu'))

    model.add(Dropout(0.25))

    model.add(Flatten())
    model.add(Dense(128))
    model.add(Activation('relu'))

    model.add(Dropout(0.5))
    model.add(Dense(FLAGS.NUM_CLASSES))
    return model 

def modelD():
    model = Sequential()

    model.add(Flatten(input_shape=(FLAGS.IMAGE_ROWS,
                                   FLAGS.IMAGE_COLS,
                                   FLAGS.NUM_CHANNELS)))

    model.add(Dense(300, init='he_normal', activation='relu'))
    model.add(Dropout(0.5))
    model.add(Dense(300, init='he_normal', activation='relu'))
    model.add(Dropout(0.5))
    model.add(Dense(300, init='he_normal', activation='relu'))
    model.add(Dropout(0.5))
    model.add(Dense(300, init='he_normal', activation='relu'))
    model.add(Dropout(0.5))

    model.add(Dense(FLAGS.NUM_CLASSES))
    return model 

def build_model(self):
        input = Input(shape=self.state_size)
        conv = Conv2D(16, (8, 8), strides=(4, 4), activation='relu')(input)
        conv = Conv2D(32, (4, 4), strides=(2, 2), activation='relu')(conv)
        conv = Flatten()(conv)
        fc = Dense(256, activation='relu')(conv)
        policy = Dense(self.action_size, activation='softmax')(fc)
        value = Dense(1, activation='linear')(fc)

        actor = Model(inputs=input, outputs=policy)
        critic = Model(inputs=input, outputs=value)

        actor.summary()
        critic.summary()

        return actor, critic 

def test_simple_keras_udf(self):
        """ Simple Keras sequential model """
        # Notice that the input layer for a image UDF model
        # must be of shape (width, height, numChannels)
        # The leading batch size is taken care of by Keras
        with IsolatedSession(using_keras=True) as issn:
            model = Sequential()
            # Make the test model simpler to increase the stability of travis tests
            model.add(Flatten(input_shape=(640, 480, 3)))
            # model.add(Dense(64, activation='relu'))
            model.add(Dense(16, activation='softmax'))
            # Initialize the variables
            init_op = tf.global_variables_initializer()
            issn.run(init_op)
            makeGraphUDF(issn.graph,
                         'my_keras_model_udf',
                         model.outputs,
                         {tfx.op_name(model.inputs[0], issn.graph): 'image_col'})
            # Run the training procedure
            # Export the graph in this IsolatedSession as a GraphFunction
            # gfn = issn.asGraphFunction(model.inputs, model.outputs)
            fh_name = "test_keras_simple_sequential_model"
            registerKerasImageUDF(fh_name, model)

        self._assert_function_exists(fh_name) 

def create_model():
    model = Sequential()

    model.add(Convolution2D(32, 3, 3,
                            border_mode='valid', 
                            input_shape=(100, 100, 3)))  
    model.add(Activation('relu'))  
    model.add(Convolution2D(32, 3, 3))  
    model.add(Activation('relu'))  
    model.add(MaxPooling2D(pool_size=(2, 2)))  
    model.add(Dropout(0.25))  
      
    model.add(Convolution2D(64, 3, 3, 
                            border_mode='valid'))  
    model.add(Activation('relu'))  
    model.add(Convolution2D(64, 3, 3))  
    model.add(Activation('relu'))  
    model.add(MaxPooling2D(pool_size=(2, 2)))  
    model.add(Dropout(0.25))  
      
    model.add(Flatten())  
    model.add(Dense(256))  
    model.add(Activation('relu'))  
    model.add(Dropout(0.5))

    model.add(Dense(2))  
    model.add(Activation('softmax'))  

    return model 

def build_model(self):
        input = Input(shape=self.state_size)
        conv = Conv2D(16, (8, 8), strides=(4, 4), activation='relu')(input)
        conv = Conv2D(32, (4, 4), strides=(2, 2), activation='relu')(conv)
        conv = Flatten()(conv)
        fc = Dense(256, activation='relu')(conv)
        policy = Dense(self.action_size, activation='softmax')(fc)
        value = Dense(1, activation='linear')(fc)

        actor = Model(inputs=input, outputs=policy)
        critic = Model(inputs=input, outputs=value)

        actor.summary()
        critic.summary()

        return actor, critic 

def build_model(self):
        input = Input(shape=self.state_size)
        conv = Conv2D(16, (8, 8), strides=(4, 4), activation='relu')(input)
        conv = Conv2D(32, (4, 4), strides=(2, 2), activation='relu')(conv)
        conv = Flatten()(conv)
        fc = Dense(256, activation='relu')(conv)

        policy = Dense(self.action_size, activation='softmax')(fc)
        value = Dense(1, activation='linear')(fc)

        actor = Model(inputs=input, outputs=policy)
        critic = Model(inputs=input, outputs=value)

        # 가치와 정책을 예측하는 함수를 만들어냄
        actor._make_predict_function()
        critic._make_predict_function()

        actor.summary()
        critic.summary()

        return actor, critic

    # 정책신경망을 업데이트하는 함수 

def build_local_model(self):
        input = Input(shape=self.state_size)
        conv = Conv2D(16, (8, 8), strides=(4, 4), activation='relu')(input)
        conv = Conv2D(32, (4, 4), strides=(2, 2), activation='relu')(conv)
        conv = Flatten()(conv)
        fc = Dense(256, activation='relu')(conv)
        policy = Dense(self.action_size, activation='softmax')(fc)
        value = Dense(1, activation='linear')(fc)

        local_actor = Model(inputs=input, outputs=policy)
        local_critic = Model(inputs=input, outputs=value)

        local_actor._make_predict_function()
        local_critic._make_predict_function()

        local_actor.set_weights(self.actor.get_weights())
        local_critic.set_weights(self.critic.get_weights())

        local_actor.summary()
        local_critic.summary()

        return local_actor, local_critic

    # 로컬신경망을 글로벌신경망으로 업데이트 

def DCGAN_discriminator():
    nb_filters = 64
    nb_conv = int(np.floor(np.log(128) / np.log(2)))
    list_filters = [nb_filters * min(8, (2 ** i)) for i in range(nb_conv)]

    input_img = Input(shape=(128, 128, 3))
    x = Conv2D(list_filters[0], (3, 3), strides=(2, 2), name="disc_conv2d_1", padding="same")(input_img)
    x = BatchNormalization(axis=-1)(x)
    x = LeakyReLU(0.2)(x)
    # Next convs
    for i, f in enumerate(list_filters[1:]):
        name = "disc_conv2d_%s" % (i + 2)
        x = Conv2D(f, (3, 3), strides=(2, 2), name=name, padding="same")(x)
        x = BatchNormalization(axis=-1)(x)
        x = LeakyReLU(0.2)(x)

    x_flat = Flatten()(x)
    x_out = Dense(1, activation="sigmoid", name="disc_dense")(x_flat)
    discriminator_model = Model(inputs=input_img, outputs=[x_out])
    return discriminator_model 

def create_model(self) -> Sequential:
        """ model structure. you can overwrite this method to build your own model """
        logger.info(f"creating keras sequential model")
        if K.image_data_format() == "channels_first":
            input_shape = (1, *self.data_size)
        else:
            input_shape = (*self.data_size, 1)

        model = Sequential()
        model.add(Conv2D(32, (3, 3), input_shape=input_shape))
        model.add(Activation("relu"))
        model.add(MaxPooling2D(pool_size=(2, 2)))

        model.add(Conv2D(32, (3, 3)))
        model.add(Activation("relu"))
        model.add(MaxPooling2D(pool_size=(2, 2)))

        model.add(Conv2D(64, (3, 3)))
        model.add(Activation("relu"))
        model.add(MaxPooling2D(pool_size=(2, 2)))
        model.add(Flatten())
        model.add(Dense(64))
        model.add(Activation("relu"))
        model.add(Dropout(0.5))
        model.add(Dense(6))
        model.add(Activation("softmax"))

        model.compile(
            loss="sparse_categorical_crossentropy",
            optimizer="rmsprop",
            metrics=["accuracy"],
        )
        logger.info("model created")
        return model 

def create_model(self, ret_model = False):
        #base_model = VGG16(weights='imagenet', include_top=False, input_shape = (224, 224, 3))
        #base_model.trainable=False
        image_model = Sequential()
        #image_model.add(base_model)
        #image_model.add(Flatten())
        image_model.add(Dense(EMBEDDING_DIM, input_dim = 4096, activation='relu'))

        image_model.add(RepeatVector(self.max_cap_len))

        lang_model = Sequential()
        lang_model.add(Embedding(self.vocab_size, 256, input_length=self.max_cap_len))
        lang_model.add(LSTM(256,return_sequences=True))
        lang_model.add(TimeDistributed(Dense(EMBEDDING_DIM)))

        model = Sequential()
        model.add(Merge([image_model, lang_model], mode='concat'))
        model.add(LSTM(1000,return_sequences=False))
        model.add(Dense(self.vocab_size))
        model.add(Activation('softmax'))

        print "Model created!"

        if(ret_model==True):
            return model

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

def get_logit_cnn_layers(nb_units, p, wd, nb_classes, layers = [], dropout = False):
    # number of convolutional filters to use
    nb_filters = 32
    # size of pooling area for max pooling
    pool_size = (2, 2)
    # convolution kernel size
    kernel_size = (3, 3)

    if dropout == 'MC':
        D = Dropout_mc
    if dropout == 'pW':
        D = pW
    if dropout == 'none':
        D = Identity

    layers.append(Convolution2D(nb_filters, kernel_size[0], kernel_size[1],
                                border_mode='valid', W_regularizer=l2(wd)))
    layers.append(Activation('relu'))
    layers.append(Convolution2D(nb_filters, kernel_size[0], kernel_size[1],
                                W_regularizer=l2(wd)))
    layers.append(Activation('relu'))
    layers.append(MaxPooling2D(pool_size=pool_size))

    layers.append(Flatten())
    layers.append(D(p))
    layers.append(Dense(nb_units, W_regularizer=l2(wd)))
    layers.append(Activation('relu'))
    layers.append(D(p))
    layers.append(Dense(nb_classes, W_regularizer=l2(wd)))
    return layers