keras tensorflow模型的重现性

Question

即使设置种子，我也无法重现 keras 训练结果。我设置了随机种子并使用 CPU 进行训练。

提供的代码如下；

import os

os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
os.environ["CUDA_VISIBLE_DEVICES"] = ""

import tensorflow as tf
import numpy as np
import random

sd = 1 # Here sd means seed.
np.random.seed(sd)
random.seed(sd)
os.environ['PYTHONHASHSEED']=str(sd)
session_conf = tf.compat.v1.ConfigProto(intra_op_parallelism_threads=1, inter_op_parallelism_threads=1)
tf.random.set_seed(0)
sess = tf.compat.v1.Session(graph=tf.compat.v1.get_default_graph(), config=session_conf)
tf.compat.v1.keras.backend.set_session(sess)

import pandas as pd

from tensorflow import keras
from tensorflow.keras import layers

from sklearn.model_selection import train_test_split
from nltk.tokenize import word_tokenize
from tensorflow.keras.preprocessing.text import one_hot
from tensorflow.keras.preprocessing.sequence import pad_sequences
import pickle

import time
from tensorflow.keras.callbacks import TensorBoard


training_site = pd.read_csv('data/allTrainingSites.txt', sep='\t')
train_data, test_data = train_test_split(training_site, test_size=0.2, random_state=25)
train_data = train_data.iloc[:, 3:6].T.to_numpy()
test_data = test_data.iloc[:, 3:6].T.to_numpy()

train_data_0, train_data_1 = train_data[0], train_data[1]
test_data_0, test_data_1 = test_data[0], test_data[1]

# encode seq

def get_categ(data):
    nuc = []
    for i in data:
        for j in i: nuc.append(j)
    nuc = set(nuc)
    return nuc

nuc_len = len(get_categ(train_data[0]).union(get_categ(train_data[1])))+2
def sep_nuc(data):
    nuc = []
    for i in data: nuc.append((i))
    return nuc

embedded_seq_tr_0 = [one_hot(' '.join(sep_nuc(seq)), nuc_len) for seq in train_data_0]
embedded_seq_te_0 = [one_hot(' '.join(sep_nuc(seq)), nuc_len) for seq in test_data_0]
embedded_seq_tr_1 = [one_hot(' '.join(sep_nuc(seq)), nuc_len) for seq in train_data_1]
embedded_seq_te_1 = [one_hot(' '.join(sep_nuc(seq)), nuc_len) for seq in test_data_1]

# find the largest and padding
count_len = lambda data: len(data)
len_0 = len(max(train_data_0, key = count_len))
len_1 = len(max(train_data_1, key = count_len))

padded_seq_tr_0 = pad_sequences(embedded_seq_tr_0, len_0, padding='post')
padded_seq_te_0 = pad_sequences(embedded_seq_te_0, len_0, padding='post')
padded_seq_tr_1 = pad_sequences(embedded_seq_tr_1, len_1, padding='post')
padded_seq_te_1 = pad_sequences(embedded_seq_te_1, len_1, padding='post')

# combine array
train_01 = np.concatenate((padded_seq_tr_0,padded_seq_tr_1),axis=1)
test_01 = np.concatenate((padded_seq_te_0,padded_seq_te_1),axis=1)

train_01 = train_01.reshape(train_01.shape[0], train_01.shape[1], 1)
test_01 = test_01.reshape(test_01.shape[0], test_01.shape[1], 1)

y_train = np.asarray(train_data[2]).astype('int32')
y_test = np.asarray(test_data[2]).astype('int32')
y_train = y_train.reshape(y_train.shape[0], 1)
y_test = y_test.reshape(y_test.shape[0], 1)

# build cnn

model_cnn = keras.Sequential()
model_cnn.add(layers.Embedding(nuc_len, 20, input_length=train_01.shape[1]))
model_cnn.add(layers.Conv1D(64, 5, activation='relu', padding='same'))
model_cnn.add(layers.MaxPool1D())
model_cnn.add(layers.Dropout(0.2, seed=0))
model_cnn.add(layers.Conv1D(128, 5, activation='relu', padding='same'))
model_cnn.add(layers.MaxPool1D())
model_cnn.add(layers.Dropout(0.2, seed=0))
model_cnn.add(layers.Conv1D(256, 5, activation='relu', padding='same'))
model_cnn.add(layers.MaxPool1D())
model_cnn.add(layers.Dropout(0.2, seed=0))
model_cnn.add(layers.Conv1D(512, 5, activation='relu', padding='same'))
model_cnn.add(layers.MaxPool1D())
model_cnn.add(layers.Flatten())

model_cnn.add(layers.Dense(64, activation='relu'))
model_cnn.add(layers.Dense(16, activation='relu'))
model_cnn.add(layers.Dense(1, activation='sigmoid'))

opt_cnn = tf.keras.optimizers.Adam(learning_rate=1e-3)
# opt = tf.keras.optimizers.SGD(learning_rate=1e-3)
# model.summary()
model.summary()
model_cnn.compile(optimizer=opt_cnn, loss='BinaryCrossentropy',
              metrics=['accuracy'])



train_history_cnn = model.fit(train_01, y_train, epochs=3,
                              validation_data=(test_01, y_test),
                              batch_size=16, callbacks=[tensorboard])

即使设置种子，我也无法重现 keras 训练结果。我设置了随机种子并使用 CPU 进行训练。

我使用张量流 2.5。

Answer 1

训练可重现的模型和结果有时具有挑战性。可能对您有所帮助的一件事是使用相同的环境（例如已安装的软件包）。您可以使用 Docker 或 Docker hub 等技术复制您的环境。此外，您还可以使用 conda 虚拟环境。