# coding:utf-8
from sklearn.utils.class_weight import compute_class_weight
class_weight = 'balanced'
label = [0] * 9 + [1]*1 + [2, 2]
print(label) # [0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 2, 2]
classes=[0, 1, 2]
weight = compute_class_weight(class_weight, classes, label)
print(weight) #[ 0.44444444 4.         2.        ]
print(.44444444 * 9) # 3.99999996
print(4 * 1) # 4
print(2 * 2) # 4

如上图所示,可以看到这个函数把样本的平衡后的权重乘积为4,每个类别均如此。banlanced的计算公式为:n_samples/n_classes/np.bincount(y)。n_samples表示样本总数,n_classes表示总类别数量,np.bincount(y)输出所有类别的每个类别的样本数量,y是所有样本的标签。一个标签代表一个类别。采用balanced模型时,每种类别的权重为n_samples/n_classes,即12/3=4;然后根据每种类别中的样本数量对每个样本进行平均分配权重,即4/9=0.444, 4/1=4, 4/2=2。0类别有9个样本,1类别有1个样本,2类别有2个样本。





#calculate class weights
class_weights = class_weight.compute_class_weight( class_weight ='balanced',
                                                   classes =np.unique(y_train),
                                                  y =y_train.flatten())


Type:        module
String form: <module 'sklearn.utils.class_weight' from '/home/software/anaconda3/envs/tf115/lib/python3.7/site-packages/sklearn/utils/'>



sklearn.utils.class_weight.compute_class_weight(class_weight, classes, y)[source]

Estimate class weights for unbalanced datasets.

class_weight   dict, ‘balanced’ or None

If ‘balanced’, class weights will be given by n_samples / (n_classes * np.bincount(y)). If a dictionary is given, keys are classes and values are corresponding class weights. If None is given, the class weights will be uniform.

classes   ndarray

Array of the classes occurring in the data, as given by np.unique(y_org) with y_org the original class labels.

array-like, shape (n_samples,)

Array of original class labels per sample;

class_weight_vectndarray, shape (n_classes,)

Array with class_weight_vect[i] the weight for i-th class


The “balanced” heuristic is inspired by Logistic Regression in Rare Events Data, King, Zen, 2001.




import tensorflow as tf

import keras.backend as K
from keras.models import Sequential, Model
from keras.layers import Input, Dense, Dropout, Conv2D, MaxPooling2D, BatchNormalization, Flatten, GlobalAveragePooling2D, Multiply
from keras.callbacks import EarlyStopping, ModelCheckpoint
from keras.optimizers import Adam
from keras import backend as K
from keras.engine.topology import Layer, InputSpec
from keras.utils import Sequence, plot_model
from keras.constraints import unit_norm
from keras import regularizers


def SqueezeExcite(tensor, ratio=16):
    nb_channel = K.int_shape(tensor)[-1]  # 获得tensor的形状; -1 表示最后一个维度的长度,此处指图像的通道(5,400,1)
    x = GlobalAveragePooling2D()(tensor) ## 每个通道进行求和平均;实际上只有一个通道;

    x = Dense(nb_channel // ratio, activation='relu')(x)

    x = Dense(nb_channel, activation='sigmoid')(x)

    x = Multiply()([tensor, x])

    return x


def create_model(width=200):  ## width=400
    K.clear_session()  ## import keras.backend as K
    pool2_list = []
    merge_list = []

    input_size = Input(shape=(5, width, 1))     ## 输入层 5,400,1  图像 宽 高 通道    keras.layers.Input


    conv1_ = Conv2D(128, (5, 10), padding='same',activation='relu')(input_size) ## 128个核; 5*10大小的核;“same”代表保留边界处的卷积结果,通常会导致输出shape与输入shape相同。


    conv1  = SqueezeExcite(conv1_)
    conv2_ = Conv2D(64, (5, 10), padding='same',activation='relu')(conv1)
    conv2  = SqueezeExcite(conv2_)
    conv3_ = Conv2D(64, (5, 10), padding='same',activation='relu')(conv2)
    conv3  = SqueezeExcite(conv3_)
    conv4_ = Conv2D(128, (5, 10), padding='valid',activation='relu')(conv3)
    conv4  = SqueezeExcite(conv4_)
    pool1  = MaxPooling2D(pool_size=(1, 2))(conv4)
    conv5_ = Conv2D(64, (1, 4), padding='same',activation='relu')(pool1)
    conv5  = SqueezeExcite(conv5_)
    conv6_ = Conv2D(64, (1, 4), padding='same',activation='relu')(conv5)
    conv6  = SqueezeExcite(conv6_)
    conv7_ = Conv2D(128, (1, 4), padding='same',activation='relu')(conv6)
    conv7  = SqueezeExcite(conv7_)
    pool2  = MaxPooling2D(pool_size=(1, 2))(conv7)

    x = Flatten()(pool2)
    dense1 = Dense(256, activation='relu')(x)
    x = Dropout(0.4)(dense1)
    pred_output = Dense(1, activation='sigmoid')(x)
    model = Model(input=[input_size], output=[pred_output])

    return model





Init signature:
Stop training when a monitored quantity has stopped improving.

# Arguments
    monitor: quantity to be monitored.
    min_delta: minimum change in the monitored quantity
        to qualify as an improvement, i.e. an absolute
        change of less than min_delta, will count as no
    patience: number of epochs that produced the monitored
        quantity with no improvement after which training will
        be stopped.
        Validation quantities may not be produced for every
        epoch, if the validation frequency
        (``) is greater than one.
    verbose: verbosity mode.
    mode: one of {auto, min, max}. In `min` mode,
        training will stop when the quantity
        monitored has stopped decreasing; in `max`
        mode it will stop when the quantity
        monitored has stopped increasing; in `auto`
        mode, the direction is automatically inferred
        from the name of the monitored quantity.
    baseline: Baseline value for the monitored quantity to reach.
        Training will stop if the model doesn't show improvement
        over the baseline.
    restore_best_weights: whether to restore model weights from
        the epoch with the best value of the monitored quantity.
        If False, the model weights obtained at the last step of
        training are used.
File:           //anaconda3/envs/tf115/lib/python3.7/site-packages/keras/callbacks/
Type:           type


Init signature:
Adam optimizer.

Default parameters follow those provided in the original paper.

# Arguments
    learning_rate: float >= 0. Learning rate.
    beta_1: float, 0 < beta < 1. Generally close to 1.
    beta_2: float, 0 < beta < 1. Generally close to 1.
    amsgrad: boolean. Whether to apply the AMSGrad variant of this
        algorithm from the paper "On the Convergence of Adam and

# References
    - [Adam - A Method for Stochastic Optimization](
    - [On the Convergence of Adam and Beyond](
File:           /home/software/anaconda3/envs/tf115/lib/python3.7/site-packages/keras/
Type:           type



Signature: compile(source, filename, mode, flags=0, dont_inherit=False, optimize=-1)
Compile source into a code object that can be executed by exec() or eval().

The source code may represent a Python module, statement or expression.
The filename will be used for run-time error messages.
The mode must be 'exec' to compile a module, 'single' to compile a
single (interactive) statement, or 'eval' to compile an expression.
The flags argument, if present, controls which future statements influence
the compilation of the code.
The dont_inherit argument, if true, stops the compilation inheriting
the effects of any future statements in effect in the code calling
compile; if absent or false these statements do influence the compilation,
in addition to any features explicitly specified.
Type:      builtin_function_or_method






# construct the model
model = create_model(width=int(window_size/10))
es = EarlyStopping(monitor='val_loss', patience=2, restore_best_weights=True)
adam = Adam(lr=5e-5, beta_1=0.9, beta_2=0.999, epsilon=1e-08, decay=9e-5)
model.compile(loss='binary_crossentropy', optimizer=adam,
    metrics=['accuracy', auroc, auprc, f1_m, recall_m, precision_m])

if os.path.exists('./saved_models/DNase_hg38.v8.h5'):
    #train the model
    history =, y_train,























posted @ 2023-09-10 23:36  emanlee  阅读(22)  评论(0编辑  收藏  举报