Python training.Model方法代碼示例

# 需要導入模塊: from keras.engine import training [as 別名]
# 或者: from keras.engine.training import Model [as 別名]
def test_trainable_argument():
    x = np.random.random((5, 3))
    y = np.random.random((5, 2))

    model = Sequential()
    model.add(Dense(2, input_dim=3, trainable=False))
    model.compile('rmsprop', 'mse')
    out = model.predict(x)
    model.train_on_batch(x, y)
    out_2 = model.predict(x)
    assert_allclose(out, out_2)

    # test with nesting
    inputs = Input(shape=(3,))
    outputs = model(inputs)
    model = Model(inputs, outputs)
    model.compile('rmsprop', 'mse')
    out = model.predict(x)
    model.train_on_batch(x, y)
    out_2 = model.predict(x)
    assert_allclose(out, out_2) 

# 需要導入模塊: from keras.engine import training [as 別名]
# 或者: from keras.engine.training import Model [as 別名]
def create_policy_value_net(self):
        """create the policy value network """   
        in_x = network = Input((4, self.board_width, self.board_height))

        # conv layers
        network = Conv2D(filters=32, kernel_size=(3, 3), padding="same", data_format="channels_first", activation="relu", kernel_regularizer=l2(self.l2_const))(network)
        network = Conv2D(filters=64, kernel_size=(3, 3), padding="same", data_format="channels_first", activation="relu", kernel_regularizer=l2(self.l2_const))(network)
        network = Conv2D(filters=128, kernel_size=(3, 3), padding="same", data_format="channels_first", activation="relu", kernel_regularizer=l2(self.l2_const))(network)
        # action policy layers
        policy_net = Conv2D(filters=4, kernel_size=(1, 1), data_format="channels_first", activation="relu", kernel_regularizer=l2(self.l2_const))(network)
        policy_net = Flatten()(policy_net)
        self.policy_net = Dense(self.board_width*self.board_height, activation="softmax", kernel_regularizer=l2(self.l2_const))(policy_net)
        # state value layers
        value_net = Conv2D(filters=2, kernel_size=(1, 1), data_format="channels_first", activation="relu", kernel_regularizer=l2(self.l2_const))(network)
        value_net = Flatten()(value_net)
        value_net = Dense(64, kernel_regularizer=l2(self.l2_const))(value_net)
        self.value_net = Dense(1, activation="tanh", kernel_regularizer=l2(self.l2_const))(value_net)

        self.model = Model(in_x, [self.policy_net, self.value_net])
        
        def policy_value(state_input):
            state_input_union = np.array(state_input)
            results = self.model.predict_on_batch(state_input_union)
            return results
        self.policy_value = policy_value 

# 需要導入模塊: from keras.engine import training [as 別名]
# 或者: from keras.engine.training import Model [as 別名]
def main_test():
    # loadFlickr8k() # load Flickr8k dataset for Image Description

    # loadMSVD() # load MSVD dataset for Video Description

    loadFood101()  # load Food101 dataset for Image Classification

    # Build basic model for image classification
    classifyFood101()


#################################
#
#    Model building functions
#
################################# 

# 需要導入模塊: from keras.engine import training [as 別名]
# 或者: from keras.engine.training import Model [as 別名]
def setOutputsMapping(self, outputsMapping, acc_output=None):
        """
            Sets the mapping of the outputs from the format given by the dataset to the format received by the model.

            :param outputsMapping: dictionary with the model outputs'
                                   identifiers as keys and the dataset outputs identifiers' position as values.
                                   If the current model is Sequential then keys must be ints with
                                   the desired output order (in this case only one value can be provided).
                                   If it is Model then keys must be str.
            :param acc_output: name of the model's output that will be used for calculating
                              the accuracy of the model (only needed for Graph models)
        """
        if isinstance(self.model, Sequential) and len(outputsMapping.keys()) > 1:
            raise Exception("When using Sequential models only one output can be provided in outputsMapping")
        self.outputsMapping = outputsMapping
        self.acc_output = acc_output 

# 需要導入模塊: from keras.engine import training [as 別名]
# 或者: from keras.engine.training import Model [as 別名]
def VGG_19(self, nOutput, input):

        # Define inputs and outputs IDs
        self.ids_inputs = ['input_1']
        self.ids_outputs = ['predictions']

        # Load VGG19 model pre-trained on ImageNet
        self.model = VGG19()

        # Recover input layer
        image = self.model.get_layer(self.ids_inputs[0]).output

        # Recover last layer kept from original model
        out = self.model.get_layer('fc2').output
        out = Dense(nOutput, name=self.ids_outputs[0], activation='softmax')(out)

        self.model = Model(input=image, output=out) 

# 需要導入模塊: from keras.engine import training [as 別名]
# 或者: from keras.engine.training import Model [as 別名]
def VGG_19_ImageNet(self, nOutput, input):

        # Define inputs and outputs IDs
        self.ids_inputs = ['input_1']
        self.ids_outputs = ['predictions']

        # Load VGG19 model pre-trained on ImageNet
        self.model = VGG19(weights='imagenet', layers_lr=0.001)

        # Recover input layer
        image = self.model.get_layer(self.ids_inputs[0]).output

        # Recover last layer kept from original model
        out = self.model.get_layer('fc2').output
        out = Dense(nOutput, name=self.ids_outputs[0], activation='softmax')(out)

        self.model = Model(input=image, output=out)

    ########################################
    # GoogLeNet implementation from http://dandxy89.github.io/ImageModels/googlenet/
    ######################################## 

# 需要導入模塊: from keras.engine import training [as 別名]
# 或者: from keras.engine.training import Model [as 別名]
def add_One_vs_One_Merge_Functional(self, inputs_list, nOutput, activation='softmax'):

        # join outputs from OneVsOne classifers
        ecoc_loss_name = 'ecoc_loss'
        final_loss_name = 'final_loss/out'
        ecoc_loss = merge(inputs_list, name=ecoc_loss_name, mode='concat', concat_axis=1)
        drop = Dropout(0.5, name='final_loss/drop')(ecoc_loss)
        # apply final joint prediction
        final_loss = Dense(nOutput, activation=activation, name=final_loss_name)(drop)

        in_node = self.model.layers[0].name
        in_node = self.model.get_layer(in_node).output
        self.model = Model(input=in_node, output=[ecoc_loss, final_loss])
        # self.model = Model(input=in_node, output=['ecoc_loss', 'final_loss'])

        return [ecoc_loss_name, final_loss_name] 

# 需要導入模塊: from keras.engine import training [as 別名]
# 或者: from keras.engine.training import Model [as 別名]
def create_model(gpu):
    with tf.device(gpu):
        input = Input((1280, 1918, len(dirs)))
        x = Lambda(lambda x: K.mean(x, axis=-1, keepdims=True))(input)
        model = Model(input, x)
        model.summary()
    return model 

# 需要導入模塊: from keras.engine import training [as 別名]
# 或者: from keras.engine.training import Model [as 別名]
def get_unet_resnet(input_shape):
    resnet_base = ResNet50(input_shape=input_shape, include_top=False)

    if args.show_summary:
        resnet_base.summary()

    for l in resnet_base.layers:
        l.trainable = True
    conv1 = resnet_base.get_layer("activation_1").output
    conv2 = resnet_base.get_layer("activation_10").output
    conv3 = resnet_base.get_layer("activation_22").output
    conv4 = resnet_base.get_layer("activation_40").output
    conv5 = resnet_base.get_layer("activation_49").output

    up6 = concatenate([UpSampling2D()(conv5), conv4], axis=-1)
    conv6 = conv_block_simple(up6, 256, "conv6_1")
    conv6 = conv_block_simple(conv6, 256, "conv6_2")

    up7 = concatenate([UpSampling2D()(conv6), conv3], axis=-1)
    conv7 = conv_block_simple(up7, 192, "conv7_1")
    conv7 = conv_block_simple(conv7, 192, "conv7_2")

    up8 = concatenate([UpSampling2D()(conv7), conv2], axis=-1)
    conv8 = conv_block_simple(up8, 128, "conv8_1")
    conv8 = conv_block_simple(conv8, 128, "conv8_2")

    up9 = concatenate([UpSampling2D()(conv8), conv1], axis=-1)
    conv9 = conv_block_simple(up9, 64, "conv9_1")
    conv9 = conv_block_simple(conv9, 64, "conv9_2")

    vgg = VGG16(input_shape=input_shape, input_tensor=resnet_base.input, include_top=False)
    for l in vgg.layers:
        l.trainable = False
    vgg_first_conv = vgg.get_layer("block1_conv2").output
    up10 = concatenate([UpSampling2D()(conv9), resnet_base.input, vgg_first_conv], axis=-1)
    conv10 = conv_block_simple(up10, 32, "conv10_1")
    conv10 = conv_block_simple(conv10, 32, "conv10_2")
    conv10 = SpatialDropout2D(0.2)(conv10)
    x = Conv2D(1, (1, 1), activation="sigmoid", name="prediction")(conv10)
    model = Model(resnet_base.input, x)
    return model 

# 需要導入模塊: from keras.engine import training [as 別名]
# 或者: from keras.engine.training import Model [as 別名]
def get_simple_unet(input_shape):
    img_input = Input(input_shape)
    conv1 = conv_block_simple(img_input, 32, "conv1_1")
    conv1 = conv_block_simple(conv1, 32, "conv1_2")
    pool1 = MaxPooling2D((2, 2), strides=(2, 2), padding="same", name="pool1")(conv1)

    conv2 = conv_block_simple(pool1, 64, "conv2_1")
    conv2 = conv_block_simple(conv2, 64, "conv2_2")
    pool2 = MaxPooling2D((2, 2), strides=(2, 2), padding="same", name="pool2")(conv2)

    conv3 = conv_block_simple(pool2, 128, "conv3_1")
    conv3 = conv_block_simple(conv3, 128, "conv3_2")
    pool3 = MaxPooling2D((2, 2), strides=(2, 2), padding="same", name="pool3")(conv3)

    conv4 = conv_block_simple(pool3, 256, "conv4_1")
    conv4 = conv_block_simple(conv4, 256, "conv4_2")
    conv4 = conv_block_simple(conv4, 256, "conv4_3")

    up5 = concatenate([UpSampling2D()(conv4), conv3], axis=-1)
    conv5 = conv_block_simple(up5, 128, "conv5_1")
    conv5 = conv_block_simple(conv5, 128, "conv5_2")

    up6 = concatenate([UpSampling2D()(conv5), conv2], axis=-1)
    conv6 = conv_block_simple(up6, 64, "conv6_1")
    conv6 = conv_block_simple(conv6, 64, "conv6_2")

    up7 = concatenate([UpSampling2D()(conv6), conv1], axis=-1)
    conv7 = conv_block_simple(up7, 32, "conv7_1")
    conv7 = conv_block_simple(conv7, 32, "conv7_2")

    conv7 = SpatialDropout2D(0.2)(conv7)

    prediction = Conv2D(1, (1, 1), activation="sigmoid", name="prediction")(conv7)
    model = Model(img_input, prediction)
    return model 

# 需要導入模塊: from keras.engine import training [as 別名]
# 或者: from keras.engine.training import Model [as 別名]
def get_unet_mobilenet(input_shape):
    base_model = MobileNet(include_top=False, input_shape=input_shape)

    conv1 = base_model.get_layer('conv_pw_1_relu').output
    conv2 = base_model.get_layer('conv_pw_3_relu').output
    conv3 = base_model.get_layer('conv_pw_5_relu').output
    conv4 = base_model.get_layer('conv_pw_11_relu').output
    conv5 = base_model.get_layer('conv_pw_13_relu').output
    up6 = concatenate([UpSampling2D()(conv5), conv4], axis=-1)
    conv6 = conv_block_simple(up6, 256, "conv6_1")
    conv6 = conv_block_simple(conv6, 256, "conv6_2")

    up7 = concatenate([UpSampling2D()(conv6), conv3], axis=-1)
    conv7 = conv_block_simple(up7, 256, "conv7_1")
    conv7 = conv_block_simple(conv7, 256, "conv7_2")

    up8 = concatenate([UpSampling2D()(conv7), conv2], axis=-1)
    conv8 = conv_block_simple(up8, 192, "conv8_1")
    conv8 = conv_block_simple(conv8, 128, "conv8_2")

    up9 = concatenate([UpSampling2D()(conv8), conv1], axis=-1)
    conv9 = conv_block_simple(up9, 96, "conv9_1")
    conv9 = conv_block_simple(conv9, 64, "conv9_2")

    up10 = concatenate([UpSampling2D()(conv9), base_model.input], axis=-1)
    conv10 = conv_block_simple(up10, 48, "conv10_1")
    conv10 = conv_block_simple(conv10, 32, "conv10_2")
    conv10 = SpatialDropout2D(0.2)(conv10)
    x = Conv2D(1, (1, 1), activation="sigmoid", name="prediction")(conv10)
    model = Model(base_model.input, x)
    return model 

# 需要導入模塊: from keras.engine import training [as 別名]
# 或者: from keras.engine.training import Model [as 別名]
def get_unet_inception_resnet_v2(input_shape):
    base_model = InceptionResNetV2(include_top=False, input_shape=input_shape)
    conv1 = base_model.get_layer('activation_3').output
    conv2 = base_model.get_layer('activation_5').output
    conv3 = base_model.get_layer('block35_10_ac').output
    conv4 = base_model.get_layer('block17_20_ac').output
    conv5 = base_model.get_layer('conv_7b_ac').output
    up6 = concatenate([UpSampling2D()(conv5), conv4], axis=-1)
    conv6 = conv_block_simple(up6, 256, "conv6_1")
    conv6 = conv_block_simple(conv6, 256, "conv6_2")

    up7 = concatenate([UpSampling2D()(conv6), conv3], axis=-1)
    conv7 = conv_block_simple(up7, 256, "conv7_1")
    conv7 = conv_block_simple(conv7, 256, "conv7_2")

    up8 = concatenate([UpSampling2D()(conv7), conv2], axis=-1)
    conv8 = conv_block_simple(up8, 128, "conv8_1")
    conv8 = conv_block_simple(conv8, 128, "conv8_2")

    up9 = concatenate([UpSampling2D()(conv8), conv1], axis=-1)
    conv9 = conv_block_simple(up9, 64, "conv9_1")
    conv9 = conv_block_simple(conv9, 64, "conv9_2")

    up10 = concatenate([UpSampling2D()(conv9), base_model.input], axis=-1)
    conv10 = conv_block_simple(up10, 48, "conv10_1")
    conv10 = conv_block_simple(conv10, 32, "conv10_2")
    conv10 = SpatialDropout2D(0.4)(conv10)
    x = Conv2D(1, (1, 1), activation="sigmoid", name="prediction")(conv10)
    model = Model(base_model.input, x)
    return model 

# 需要導入模塊: from keras.engine import training [as 別名]
# 或者: from keras.engine.training import Model [as 別名]
def update_learning_rate(self, learning_rate, arg_weight=1.):
        print("Re-Compile Model lr=%s aw=%s" % (learning_rate, arg_weight))
        self.compile_model(learning_rate, arg_weight=arg_weight) 

# 需要導入模塊: from keras.engine import training [as 別名]
# 或者: from keras.engine.training import Model [as 別名]
def train_f_enc(self, steps_list, epoch=50):
        print("training f_enc")
        f_add0 = Sequential(name='f_add0')
        f_add0.add(self.f_enc)
        f_add0.add(Dense(FIELD_DEPTH))
        f_add0.add(Activation('softmax', name='softmax_add0'))

        f_add1 = Sequential(name='f_add1')
        f_add1.add(self.f_enc)
        f_add1.add(Dense(FIELD_DEPTH))
        f_add1.add(Activation('softmax', name='softmax_add1'))

        env_model = Model(self.f_enc.inputs, [f_add0.output, f_add1.output], name="env_model")
        env_model.compile(optimizer='adam', loss=['categorical_crossentropy']*2)

        for ep in range(epoch):
            losses = []
            for idx, steps_dict in enumerate(steps_list):
                prev = None
                for step in steps_dict['steps']:
                    x = self.convert_input(step.input)[:2]
                    env_values = step.input.env.reshape((4, -1))
                    in1 = np.clip(env_values[0].argmax() - 1, 0, 9)
                    in2 = np.clip(env_values[1].argmax() - 1, 0, 9)
                    carry = np.clip(env_values[2].argmax() - 1, 0, 9)
                    y_num = in1 + in2 + carry
                    now = (in1, in2, carry)
                    if prev == now:
                        continue
                    prev = now
                    y0 = to_one_hot_array((y_num %  10)+1, FIELD_DEPTH)
                    y1 = to_one_hot_array((y_num // 10)+1, FIELD_DEPTH)
                    y = [yy.reshape((self.batch_size, -1)) for yy in [y0, y1]]
                    loss = env_model.train_on_batch(x, y)
                    losses.append(loss)
            print("ep %3d: loss=%s" % (ep, np.average(losses)))
            if np.average(losses) < 1e-06:
                break 

# 需要導入模塊: from keras.engine import training [as 別名]
# 或者: from keras.engine.training import Model [as 別名]
def build_model(args):
    cnn_filter_num = args['cnn_filter_num']
    cnn_filter_size = args['cnn_filter_size']
    l2_reg = args['l2_reg']

    in_x = x = Input(args['input_dim'])

    # (batch, channels, height, width)
    x = Conv2D(filters=cnn_filter_num, kernel_size=cnn_filter_size, padding="same",
                data_format="channels_first", kernel_regularizer=l2(l2_reg))(x)
    x = BatchNormalization(axis=1)(x)
    x = Activation("relu")(x)

    for _ in range(args['res_layer_num']):
        x = _build_residual_block(args, x)

    res_out = x
    
    # for policy output
    x = Conv2D(filters=2, kernel_size=1, data_format="channels_first", kernel_regularizer=l2(l2_reg))(res_out)
    x = BatchNormalization(axis=1)(x)
    x = Activation("relu")(x)
    x = Flatten()(x)
    policy_out = Dense(args['policy_dim'], kernel_regularizer=l2(l2_reg), activation="softmax", name="policy")(x)
    
    # for value output
    x = Conv2D(filters=1, kernel_size=1, data_format="channels_first", kernel_regularizer=l2(l2_reg))(res_out)
    x = BatchNormalization(axis=1)(x)
    x = Activation("relu")(x)
    x = Flatten()(x)
    x = Dense(256, kernel_regularizer=l2(l2_reg), activation="relu")(x)
    value_out = Dense(1, kernel_regularizer=l2(l2_reg), activation="tanh", name="value")(x)
    
    return Model(in_x, [policy_out, value_out], name="model")