为什么我的结果仍然无法重现？

Question

我想获得CNN的可重复结果。我将Keras和Google Colab与GPU配合使用。

除了建议插入某些代码段（该代码段应具有可重复性）的建议之外，我还向各层添加了种子。

###### This is the first code snipped to run #####

!pip install -U -q PyDrive
from pydrive.auth import GoogleAuth
from pydrive.drive import GoogleDrive
from google.colab import auth
from oauth2client.client import GoogleCredentials

# Authenticate and create the PyDrive client.
# This only needs to be done once per notebook.
auth.authenticate_user()
gauth = GoogleAuth()
gauth.credentials = GoogleCredentials.get_application_default()
drive = GoogleDrive(gauth)

###### This is the second code snipped to run #####

from __future__ import print_function  
import numpy as np 

import tensorflow as tf
print(tf.test.gpu_device_name())

import random as rn 
import os 
os.environ['PYTHONASHSEED'] = '0' 
np.random.seed(1)   
rn.seed(1)   
session_conf = tf.ConfigProto(intra_op_parallelism_threads=1, inter_op_parallelism_threads=1) 

###### This is the third code snipped to run #####

from keras import backend as K

tf.set_random_seed(1) 
sess = tf.Session(graph=tf.get_default_graph(), config=session_conf)  
K.set_session(sess)   

###### This is the fourth code snipped to run #####

def model_cnn():
  model = Sequential()
  model.add(Conv2D(32, kernel_size=(3,3), kernel_initializer=initializers.glorot_uniform(seed=1), input_shape=(28,28,1)))
  model.add(BatchNormalization())
  model.add(Activation('relu'))

  model.add(Conv2D(32, kernel_size=(3,3), kernel_initializer=initializers.glorot_uniform(seed=2)))
  model.add(BatchNormalization())
  model.add(Activation('relu'))
  model.add(MaxPooling2D(pool_size=(2,2)))
  model.add(Dropout(0.25, seed=1))  

  model.add(Flatten())

  model.add(Dense(512, kernel_initializer=initializers.glorot_uniform(seed=2)))
  model.add(BatchNormalization())
  model.add(Activation('relu'))
  model.add(Dropout(0.5, seed=1))
  model.add(Dense(10, kernel_initializer=initializers.glorot_uniform(seed=2)))
  model.add(Activation('softmax'))

  model.compile(loss="categorical_crossentropy", optimizer=Adam(lr=0.001), metrics=['accuracy'])
  return model


def split_data(X,y):
  X_train_val, X_val, y_train_val, y_val = train_test_split(X, y, random_state=42, test_size=1/5, stratify=y) 
  return(X_train_val, X_val, y_train_val, y_val) 


def train_model_with_EarlyStopping(model, X, y):
  # make train and validation data
  X_tr, X_val, y_tr, y_val = split_data(X,y)

  es = EarlyStopping(monitor='val_loss', patience=20, mode='min', restore_best_weights=True)

  history = model.fit(X_tr, y_tr,
                      batch_size=64,
                      epochs=200, 
                      verbose=1,
                      validation_data=(X_val,y_val),
                      callbacks=[es])    

  return history

###### This is the fifth code snipped to run #####

train_model_with_EarlyStopping(model_cnn(), X, y)

总是我运行上面的代码，我得到不同的结果。原因是否出在代码中，还是根本无法在支持GPU的Google Colab中获得可重复的结果？

---

完整的代码（代码中有不必要的部分，例如未使用的库）：

!pip install -U -q PyDrive
from pydrive.auth import GoogleAuth
from pydrive.drive import GoogleDrive
from google.colab import auth
from oauth2client.client import GoogleCredentials
auth.authenticate_user()
gauth = GoogleAuth()
gauth.credentials = GoogleCredentials.get_application_default()
drive = GoogleDrive(gauth)
from __future__ import print_function # NEU 
import numpy as np 

import tensorflow as tf
import random as rn 
import os 
os.environ['PYTHONASHSEED'] = '0' 
np.random.seed(1)   
rn.seed(1)   
session_conf = tf.ConfigProto(intra_op_parallelism_threads=1, inter_op_parallelism_threads=1) 
from keras import backend as K

tf.set_random_seed(1)  
sess = tf.Session(graph=tf.get_default_graph(), config=session_conf)   
K.set_session(sess)  

import os
local_root_path = os.path.expanduser("~/data/data")
print(local_root_path)
try:
  os.makedirs(local_root_path, exist_ok=True)  
except: pass

def ListFolder(google_drive_id, destination):
  file_list = drive.ListFile({'q': "'%s' in parents and trashed=false" % google_drive_id}).GetList()
  counter = 0
  for f in file_list:
    # If it is a directory then, create the dicrectory and upload the file inside it
    if f['mimeType']=='application/vnd.google-apps.folder': 
      folder_path = os.path.join(destination, f['title'])
      os.makedirs(folder_path, exist_ok=True)
      print('creating directory {}'.format(folder_path))
      ListFolder(f['id'], folder_path)
    else:
      fname = os.path.join(destination, f['title'])
      f_ = drive.CreateFile({'id': f['id']})
      f_.GetContentFile(fname)
      counter += 1
  print('{} files were uploaded in {}'.format(counter, destination))
ListFolder("1DyM_D2ZJ5UHIXmXq4uHzKqXSkLTH-lSo", local_root_path)

import glob
import h5py
from time import time
from keras import initializers 
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential, model_from_json
from keras.layers import Dense, Dropout, Activation, Flatten, BatchNormalization, merge
from keras.layers import Convolution2D, MaxPooling2D, AveragePooling2D
from keras.optimizers import SGD, Adam, RMSprop, Adagrad, Adadelta, Adamax, Nadam
from keras.utils import np_utils
from keras.callbacks import LearningRateScheduler, ModelCheckpoint, TensorBoard, ReduceLROnPlateau
from keras.regularizers import l2
from keras.layers.advanced_activations import LeakyReLU, ELU
from keras import backend as K
import numpy as np
import pickle as pkl
from matplotlib import pyplot as plt
%matplotlib inline
import gzip
import numpy as np
from keras.utils import to_categorical
from keras.models import Sequential
from keras.layers import Dense, Conv2D, Flatten
from keras.datasets import fashion_mnist
from numpy import mean, std
import matplotlib.pyplot as plt
from sklearn.model_selection import KFold, StratifiedKFold
from keras.datasets import fashion_mnist
from keras.utils import to_categorical
from keras.layers import Conv2D, MaxPooling2D, Dense, Flatten
from keras.optimizers import SGD, Adam
from keras.wrappers.scikit_learn import KerasClassifier
from sklearn.metrics import accuracy_score, confusion_matrix, classification_report
from sklearn.metrics import precision_score
from sklearn.metrics import recall_score
from sklearn.metrics import f1_score
from sklearn.metrics import auc, average_precision_score, f1_score

import time
from keras.callbacks import EarlyStopping
from keras.callbacks import ModelCheckpoint
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix, classification_report
from sklearn.model_selection import GridSearchCV, RandomizedSearchCV
from google.colab import files
from PIL import Image 



def model_cnn():
  model = Sequential()
  model.add(Conv2D(32, kernel_size=(3,3), kernel_initializer=initializers.glorot_uniform(seed=1), input_shape=(28,28,1)))
  model.add(BatchNormalization())
  model.add(Activation('relu'))
  model.add(Conv2D(32, kernel_size=(3,3), kernel_initializer=initializers.glorot_uniform(seed=2)))
  model.add(BatchNormalization())
  model.add(Activation('relu'))
  model.add(MaxPooling2D(pool_size=(2,2)))
  model.add(Dropout(0.25, seed=1))  
  model.add(Flatten())
  model.add(Dense(512, kernel_initializer=initializers.glorot_uniform(seed=2)))
  model.add(BatchNormalization())
  model.add(Activation('relu'))
  model.add(Dropout(0.5, seed=1))
  model.add(Dense(10, kernel_initializer=initializers.glorot_uniform(seed=2)))
  model.add(Activation('softmax'))
  model.compile(loss="categorical_crossentropy", optimizer=Adam(lr=0.001), metrics=['accuracy'])
  return model

def train_model_with_EarlyStopping(model, X, y):
  X_tr, X_val, y_tr, y_val = split_train_val_data(X,y)
  es = EarlyStopping(monitor='val_loss', patience=20, mode='min', restore_best_weights=True)      
  history = model.fit(X_tr, y_tr,
                      batch_size=64,
                      epochs=200, 
                      verbose=1,
                      validation_data=(X_val,y_val),
                      callbacks=[es])    
  evaluate_model(model, history, X_tr, y_tr)
  return history 


```

Answer 1

问题不仅限于 Colab，而且可以在本地重现。然而，这种行为可能是不可避免的。

底部的代码是代码的可重现性最低的版本，调整了拟合参数以加快测试速度。我观察到的是，在 5 次运行中，每次运行468 次迭代的最大损失差异仅为0.0144%。这很好。使用batch_size=64、60000样本和20时期，您将有 18750 次迭代 - 这将大大放大这个数字。

无论如何，GPU 并行性最有可能是驱动随机数的罪魁祸首——随着时间的推移，微小的差异确实会积累起来，从而产生巨大的差异——下面的演示。如果1e-8看起来很小，请尝试将随机噪声添加到您的权重的一半1e-8，并将幅度剪裁为，并见证其生活哲学的变化。

如果您不使用它们，种子的作用将变得非常明显- 尝试一下，您的所有指标将在前 10 次迭代中猖獗。此外，损失更适合测量运行时差异，因为准确度对数字精度误差更为敏感：10 个样本批次的 60% 准确度和 70% 准确度之间的差异是一个与0.000001wrt不同的预测0.5- 但损失几乎不会改变。

最后，请注意，与随机性相比，您的超参数选择对模型性能的影响要大得多；无论您扔多少种子，它们都不会将模型魔术化到 SOTA 中。- 我推荐这个精美的剪辑。

你的代码- 很好。您已采取所有实际步骤来确保可重现性，但有一个例外：PYTHONHASHSEED必须在Python 内核启动之前进行设置。

你能做些什么来减少随机性？

1. 重复运行，平均结果。可以理解，这是昂贵的，但请注意，即使是完全可重复的运行也不能提供完美的信息，因为模型方差与训练和验证集可能比噪声引起的随机性大得多

2. K-Fold 交叉验证：可以显着减轻数据和噪声方差

3. 更大的验证集：由于噪声，提取的特征可能会有很大差异；验证集越大，权重中的小扰动应反映在指标中

GPU 并行性：放大浮点误差

print(2. * 11. / 9.)  # 2.4444444444444446
print(2. / 9. * 11.)  # 2.444444444444444

操作顺序很重要，并且通过利用多线程，GPU 并行性不能保证以相同顺序执行的任何操作。乍一看，差异可能看起来很无辜 - 但要给它足够的迭代......

one = 1
for _ in range(int(1e8)):
    one *= (2. / 9. * 11.) / (2. * 11. / 9.)
print(one)     # 0.9999999777955395
print(1 - one) # 1.8167285897874308e-08

......而“一”是1e-08远离其原始自我的典型小权重值。如果 1 亿次迭代似乎很长，请考虑操作在大约半分钟内完成，而您的模型可以训练一个多小时，而前者完全在 CPU 上运行。

最小的可重复实验：

import tensorflow as tf
import random as rn 
import numpy as np
np.random.seed(1)   
rn.seed(2)   
tf.set_random_seed(3)

from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten, BatchNormalization
from keras.layers import MaxPooling2D, Conv2D
from keras.optimizers import Adam

def model_cnn():
  model = Sequential()
  model.add(Conv2D(32, kernel_size=(3,3), 
                   kernel_initializer='he_uniform', input_shape=(28,28,1)))
  model.add(BatchNormalization())
  model.add(Activation('relu'))
  model.add(Conv2D(32, kernel_size=(3,3), kernel_initializer='he_uniform'))
  model.add(BatchNormalization())
  model.add(Activation('relu'))
  model.add(MaxPooling2D(pool_size=(2,2)))
  model.add(Dropout(0.25))
  model.add(Flatten())
  model.add(Dense(512, kernel_initializer='he_uniform'))
  model.add(BatchNormalization())
  model.add(Activation('relu'))
  model.add(Dropout(0.5))
  model.add(Dense(10, kernel_initializer='he_uniform'))
  model.add(Activation('softmax'))
  model.compile(loss="categorical_crossentropy", optimizer=Adam(lr=0.001), 
                metrics=['accuracy'])
  return model

np.random.seed(1)   
rn.seed(2)     
tf.set_random_seed(3) 

X_train = np.random.randn(30000, 28, 28, 1)
y_train = np.random.randint(0, 2, (30000, 10))
X_val   = np.random.randn(30000, 28, 28, 1)
y_val   = np.random.randint(0, 2, (30000, 10))
model = model_cnn()

np.random.seed(1)   
rn.seed(2)   
tf.set_random_seed(3)

history = model.fit(X_train, y_train, batch_size=64,shuffle=True, 
                    epochs=1, verbose=1, validation_data=(X_val,y_val))

运行差异：

loss: 12.5044 - acc: 0.0971 - val_loss: 11.5389 - val_acc: 0.1051
loss: 12.5047 - acc: 0.0958 - val_loss: 11.5369 - val_acc: 0.1018
loss: 12.5055 - acc: 0.0955 - val_loss: 11.5382 - val_acc: 0.0980
loss: 12.5042 - acc: 0.0961 - val_loss: 11.5382 - val_acc: 0.1179
loss: 12.5062 - acc: 0.0960 - val_loss: 11.5366 - val_acc: 0.1082