Question

我正在使用Python 3.7.7，Tensorflow 2.1.0和Keras 2.3.1学习如何使用元学习。

我正在使用2向5镜头学习。

作为特征提取器，我正在使用VGG-16 conv1到conv5层：

def vgg16_encoder(input_size = (200,200,1)):
    inputs = Input(input_size, name = 'input')

    conv1 = Conv2D(64, (3, 3), activation = 'relu', padding = 'same', name ='conv1_1')(inputs)
    conv1 = Conv2D(64, (3, 3), activation = 'relu', padding = 'same', name ='conv1_2')(conv1)
    pool1 = MaxPooling2D(pool_size = (2,2), strides = (2,2), name = 'pool_1')(conv1)

    conv2 = Conv2D(128, (3, 3), activation = 'relu', padding = 'same', name ='conv2_1')(pool1)
    conv2 = Conv2D(128, (3, 3), activation = 'relu', padding = 'same', name ='conv2_2')(conv2)
    pool2 = MaxPooling2D(pool_size = (2,2), strides = (2,2), name = 'pool_2')(conv2)

    conv3 = Conv2D(256, (3, 3), activation = 'relu', padding = 'same', name ='conv3_1')(pool2)
    conv3 = Conv2D(256, (3, 3), activation = 'relu', padding = 'same', name ='conv3_2')(conv3)
    conv3 = Conv2D(256, (3, 3), activation = 'relu', padding = 'same', name ='conv3_3')(conv3)
    pool3 = MaxPooling2D(pool_size = (2,2), strides = (2,2), name = 'pool_3')(conv3)

    conv4 = Conv2D(512, (3, 3), activation = 'relu', padding = 'same', name ='conv4_1')(pool3)
    conv4 = Conv2D(512, (3, 3), activation = 'relu', padding = 'same', name ='conv4_2')(conv4)
    conv4 = Conv2D(512, (3, 3), activation = 'relu', padding = 'same', name ='conv4_3')(conv4)
    pool4 = MaxPooling2D(pool_size = (2,2), strides = (2,2), name = 'pool_4')(conv4)

    conv5 = Conv2D(512, (3, 3), activation = 'relu', padding = 'same', name ='conv5_1')(pool4)
    conv5 = Conv2D(512, (3, 3), activation = 'relu', padding = 'same', name ='conv5_2')(conv5)
    conv5 = Conv2D(512, (3, 3), activation = 'relu', padding = 'same', name ='conv5_3')(conv5)
    pool5 = MaxPooling2D(pool_size = (2,2), strides = (2,2), name = 'pool_5')(conv5)

    opt = Adam(lr=0.001)

    model = Model(inputs = inputs, outputs = pool5, name = 'vgg-16_encoder')

    model.compile(optimizer=opt, loss=keras.losses.categorical_crossentropy, metrics=['accuracy'])

    return model

我的数据集是一个形状为(960, 2, 200, 200, 1)的Numpy数组：960对200x200x1的图像。这对是（X，Y）。我正在尝试进行语义分割。

这是我的算法

# 1. Let's say we have the dataset, D, comprising
#    {(x1, y1), (x2, y2), ... (xn, yn)} where x is the feature and y is the
#    class label.
# ------------------------------------------------------------------------------

# Merge all images into one dataset.
dataset = []

# !!!! Removed for brevity !!!!

# Convert it into a Numpy Array.
D = np.array(dataset)


# 2. Since we perform episodic training, we randomly sample n number of data
#    points per each class from our dataset, D, and prepare our support set, S.
# ------------------------------------------------------------------------------
#
# 3. Similarly, we select n number of data points and prepare our query set, Q.
# ------------------------------------------------------------------------------

# Number of pairs in dataset.
no_of_samples = D.shape[0]

for epoch in range(num_epochs):
    for episode in range(num_episodes):
        selected = np.random.permutation(no_of_samples)[:num_shot + num_query]
        # Create our Support Set.
        support_set = np.array(D[selected[:num_shot]])
        # Create our Query Set.
        query_set = np.array(D[selected[num_query:]])

        # 4. We learn the embeddings of the data points in our support set using
        # our embedding function, f∅ (). The embedding function can be any 
        # feature extractor—say, a convolutional network for images and an LSTM 
        # network for text.

现在，我不知道如何继续。

在另一个示例中，使用U-NET，我有以下代码：

img_shape = (rows_standard, cols_standard, 1)

model = utils.get_unet(img_shape)

model.summary()


from sklearn.model_selection import train_test_split

# Split train and valid
X_train, X_valid, y_train, y_valid = train_test_split(x_images, y_images, test_size=0.1, random_state=42)

results = model.fit(X_train, y_train, batch_size=32, epochs=50,\
                    validation_data=(X_valid, y_valid))

我认为我必须这样做，使用Support Set分割train_test_split，但是我不确定。

如何使用Support Set和Query Set来训练特征提取器？

如何训练原型学习特征提取器（CNN）

0 个答案: