I have a simple code to run on Google Colab (I use CPU mode):
import numpy as np
import pandas as pd
## LOAD DATASET
datatrain = pd.read_csv("gdrive/My Drive/iris_train.csv").values
xtrain = datatrain[:,:-1]
ytrain = datatrain[:,-1]
datatest = pd.read_csv("gdrive/My Drive/iris_test.csv").values
xtest = datatest[:,:-1]
ytest = datatest[:,-1]
import tensorflow as tf
from tensorflow.keras.layers import Dense, Activation
from tensorflow.keras.utils import to_categorical
## SET ALL SEED
import os
os.environ['PYTHONHASHSEED']=str(66)
import random
random.seed(66)
np.random.seed(66)
tf.set_random_seed(66)
from tensorflow.keras import backend as K
session_conf = tf.ConfigProto(intra_op_parallelism_threads=1, inter_op_parallelism_threads=1)
sess = tf.Session(graph=tf.get_default_graph(), config=session_conf)
K.set_session(sess)
## MAIN PROGRAM
ycat = to_categorical(ytrain)
# build model
model = tf.keras.Sequential()
model.add(Dense(10, input_shape=(4,)))
model.add(Activation("sigmoid"))
model.add(Dense(3))
model.add(Activation("softmax"))
#choose optimizer and loss function
model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])
# train
model.fit(xtrain, ycat, epochs=15, batch_size=32)
#get prediction
classes = model.predict_classes(xtest)
#get accuration
accuration = np.sum(classes == ytest)/len(ytest) * 100
I have read the setup to create a reproducibility code here Reproducible results using Keras with TensorFlow backend and I put all code in the same cell. But the result (e.g. the loss) is always different every time I run that cell (run the cell using shift + enter).
In my case, the result from the code above can be reproduced, if only:
I run using "runtime" > "restart and run all" or,
I put that code in a single file and run it using the command line (python3 file.py)
is there something I miss to make the result reproducible without restart the runtime?
You should also fix the seed for kernel_initializer in your Dense layers. So, your model will be like:
model = tf.keras.Sequential()
model.add(Dense(10, kernel_initializer=keras.initializers.glorot_uniform(seed=66), input_shape=(4,)))
model.add(Activation("sigmoid"))
model.add(Dense(3, kernel_initializer=keras.initializers.glorot_uniform(seed=66)))
model.add(Activation("softmax"))
I tried most of the solutions on the web and just the following codes worked for me :
seed=0
import os
os.environ['PYTHONHASHSEED'] = str(seed)
# For working on GPUs from "TensorFlow Determinism"
os.environ["TF_DETERMINISTIC_OPS"] = str(seed)
import numpy as np
np.random.seed(seed)
import random
random.seed(seed)
import tensorflow as tf
tf.random.set_seed(seed)
note that you should call this code before every run(at least for me)
if you want run your code on CPU:
seed=0
import os
os.environ['PYTHONHASHSEED'] = str(seed)
# For working on GPUs from "TensorFlow Determinism"
os.environ['CUDA_VISBLE_DEVICE'] = ''
import numpy as np
np.random.seed(seed)
import random
random.seed(seed)
import tensorflow as tf
tf.random.set_seed(seed)
I've tried to get Tensorflow 2.0 working reproducibly using Keras and Google Colab (CPU), with a version of the Iris dataset processing similar to that described above by #malioboro. This seems to work - might be useful:
# Install TensorFlow
try:
# %tensorflow_version only exists in Colab.
%tensorflow_version 2.x
except Exception:
pass
# Setup repro section from Keras FAQ with TF1 to TF2 adjustments
import numpy as np
import tensorflow as tf
import random as rn
# The below is necessary for starting Numpy generated random numbers
# in a well-defined initial state.
np.random.seed(42)
# The below is necessary for starting core Python generated random numbers
# in a well-defined state.
rn.seed(12345)
# Force TensorFlow to use single thread.
# Multiple threads are a potential source of non-reproducible results.
# For further details, see: https://stackoverflow.com/questions/42022950/
session_conf = tf.compat.v1.ConfigProto(intra_op_parallelism_threads=1,
inter_op_parallelism_threads=1)
# The below tf.set_random_seed() will make random number generation
# in the TensorFlow backend have a well-defined initial state.
# For further details, see:
# https://www.tensorflow.org/api_docs/python/tf/set_random_seed
tf.compat.v1.set_random_seed(1234)
sess = tf.compat.v1.Session(graph=tf.compat.v1.get_default_graph(), config=session_conf)
tf.compat.v1.keras.backend.set_session(sess)
# Rest of code follows ...
# Some adopted from: https://janakiev.com/notebooks/keras-iris/
# Some adopted from the question.
#
# Load Data
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import OneHotEncoder, StandardScaler
iris = load_iris()
X = iris['data']
y = iris['target']
names = iris['target_names']
feature_names = iris['feature_names']
# One hot encoding
enc = OneHotEncoder()
Y = enc.fit_transform(y[:, np.newaxis]).toarray()
# Scale data to have mean 0 and variance 1
# which is importance for convergence of the neural network
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)
# Split the data set into training and testing
X_train, X_test, Y_train, Y_test = train_test_split(
X_scaled, Y, test_size=0.5, random_state=2)
n_features = X.shape[1]
n_classes = Y.shape[1]
## MAIN PROGRAM
from tensorflow.keras.layers import Dense, Activation
# build model
model = tf.keras.Sequential()
model.add(Dense(10, input_shape=(4,)))
model.add(Activation("sigmoid"))
model.add(Dense(3))
model.add(Activation("softmax"))
#choose optimizer and loss function
model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])
# train
model.fit(X_train, Y_train, epochs=20, batch_size=32)
#get prediction
classes = model.predict_classes(X_test)
Related
Im getting this error: ValueError: logits and labels must have the same shape, received ((32, 1) vs (32, 23740))
This is my full code:
import pandas as pd
from keras.models import Sequential
from keras.layers import Dense, Embedding, LSTM
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix, accuracy_score, precision_score, recall_score, f1_score
import re
import numpy as np
from sklearn.preprocessing import StandardScaler, OneHotEncoder, LabelEncoder
from keras.preprocessing.text import Tokenizer
from keras.utils import to_categorical
from keras.utils import pad_sequences
# All data processing stuff
data = pd.read_csv('test.csv') # Load the data
# convert Sentiment type to string
data['Sentiment'] = data['Sentiment'].astype(str)
# remove special characters and convert to lowercase
data["Tweet"] = data["Tweet"].apply(lambda x: x.lower()) # Convert all tweets to lowercase
data["Tweet"] = data["Tweet"].apply(lambda x: x.replace("[^a-zA-Z0-9]", "")) # Remove special characters
data["Sentiment"] = data["Sentiment"].apply(lambda x: x.lower())
# Initialize the Tokenizer
tokenizer = Tokenizer()
# Fit the Tokenizer on the text data
tokenizer.fit_on_texts(data["Tweet"] + data["Sentiment"])
token_sequences1 = tokenizer.texts_to_matrix(data["Tweet"])
token_sequences2 = tokenizer.texts_to_matrix(data["Sentiment"])
padded_sequences1 = pad_sequences(token_sequences1)
padded_sequences2 = pad_sequences(token_sequences2)
# split the data into training and testing sets
x_train, x_test, y_train, y_test = train_test_split(
padded_sequences1, padded_sequences2, test_size=0.2, random_state=42)
# create the RNN model
model = Sequential()
# 1000 is the number of words in the vocabulary, 128 is the dimension of the embedding vector,
model.add(Embedding(1000, 128))
model.add(LSTM(128, dropout=0.2, recurrent_dropout=0.2))
model.add(Dense(1, activation='sigmoid'))
# compile the model with a specified loss function and optimizer
# binary_crossentropy is used for binary classification problems like this one (positive or negative sentiment)
# accuracy is the metric used to evaluate the model performance (the percentage of correct predictions)
# the loss function and the optimizer can be changed to see if the model performance improves or not
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
print(model.summary())
# train the model on the training data and put verbose=1 to see the training progress
model.fit(x_train, y_train, batch_size=32, epochs=10, verbose=1)
# evaluate the model on the testing data
y_pred = model.predict(x_test)
# calculate the evaluation metrics
accuracy = accuracy_score(y_test, y_pred)
precision = precision_score(y_test, y_pred)
recall = recall_score(y_test, y_pred)
f1 = f1_score(y_test, y_pred)
# print the evaluation metrics
print("Accuracy: {:.2f}".format(accuracy))
print("Precision: {:.2f}".format(precision))
print("Recall: {:.2f}".format(recall))
print("F1 Score: {:.2f}".format(f1))
Im actually trying to create sentiment analyser on news headlines tweets from this data, here is a sample image of how my data looks in CSV.
Please provide a solution to this, I have tried every solution I had find
I made a script in tensorflow 2.x but I had to downconvert it to tensorflow 1.x (tested in 1.14 and 1.15). However, the tf1 version performs very differently (10% accuracy lower on the test set). See also the plot for train and validation performance (diagram is attached below).
Looking at the operations needed for the migration from tf1 to tf2 it seems that only the Adam learning rate may be a problem but I'm defining it explicitly tensorflow migration
I've reproduced the same behavior both locally on GPU and CPU and on colab. The keras used was the one built-in in tensorflow (tf.keras). I've used the following functions (both for train,validation and test), using a sparse categorization (integers):
train_datagen = tf.keras.preprocessing.image.ImageDataGenerator(
horizontal_flip=horizontal_flip,
#rescale=None, #not needed for resnet50
preprocessing_function=None,
validation_split=None)
train_dataset = train_datagen.flow_from_directory(
directory=train_dir,
target_size=image_size,
class_mode='sparse',
batch_size=batch_size,
shuffle=True)
And the model is a simple resnet50 with a new layer on top:
IMG_SHAPE = img_size+(3,)
inputs = Input(shape=IMG_SHAPE, name='image_input',dtype = tf.uint8)
x = tf.cast(inputs, tf.float32)
# not working in this version of keras. inserted in imageGenerator
x = preprocess_input_resnet50(x)
base_model = tf.keras.applications.ResNet50(
include_top=False,
input_shape = IMG_SHAPE,
pooling=None,
weights='imagenet')
# Freeze the pretrained weights
base_model.trainable = False
x=base_model(x)
# Rebuild top
x = GlobalAveragePooling2D(data_format='channels_last',name="avg_pool")(x)
top_dropout_rate = 0.2
x = Dropout(top_dropout_rate, name="top_dropout")(x)
outputs = Dense(num_classes,activation="softmax", name="pred_out")(x)
model = Model(inputs=inputs, outputs=outputs,name="ResNet50_comp")
optimizer = tf.keras.optimizers.Adam(lr=learning_rate)
model.compile(optimizer=optimizer,
loss="sparse_categorical_crossentropy",
metrics=['accuracy'])
And then I'm calling the fit function:
history = model.fit_generator(train_dataset,
steps_per_epoch=n_train_batches,
validation_data=validation_dataset,
validation_steps=n_val_batches,
epochs=initial_epochs,
verbose=1,
callbacks=[stopping])
I've reproduced the same behavior for example with the following full script (applied to my dataset and changed to adam and removed intermediate final dense layer):
deep learning sandbox
The easiest way to replicate this behavior was to enable or disable the following line on a tf2 environment with the same script and add the following line to it. However, I've tested also on tf1 environments (1.14 and 1.15):
tf.compat.v1.disable_v2_behavior()
Sadly I cannot provide the dataset.
Update 26/11/2020
For full reproducibility I've obtained a similar behaviour by means of the food101 (101 categories) dataset enabling tf1 behaviour with 'tf.compat.v1.disable_v2_behavior()'. The following is the script executed with tensorflow-gpu 2.2.0:
#%% ref https://medium.com/deeplearningsandbox/how-to-use-transfer-learning-and-fine-tuning-in-keras-and-tensorflow-to-build-an-image-recognition-94b0b02444f2
import os
import sys
import glob
import argparse
import matplotlib.pyplot as plt
import tensorflow as tf
# enable and disable this to obtain tf1 behaviour
tf.compat.v1.disable_v2_behavior()
from tensorflow.keras import __version__
from tensorflow.keras.applications.resnet50 import ResNet50, preprocess_input
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Dense, GlobalAveragePooling2D
from tensorflow.keras.optimizers import Adam
# since i'm using resnet50 weights from imagenet, i'm using food101 for
# similar but different categorization tasks
# pip install tensorflow-datasets if tensorflow_dataset not found
import tensorflow_datasets as tfds
(train_ds,validation_ds),info= tfds.load('food101', split=['train','validation'], shuffle_files=True, with_info=True)
assert isinstance(train_ds, tf.data.Dataset)
print(train_ds)
#%%
IM_WIDTH, IM_HEIGHT = 224, 224
NB_EPOCHS = 10
BAT_SIZE = 32
def get_nb_files(directory):
"""Get number of files by searching directory recursively"""
if not os.path.exists(directory):
return 0
cnt = 0
for r, dirs, files in os.walk(directory):
for dr in dirs:
cnt += len(glob.glob(os.path.join(r, dr + "/*")))
return cnt
def setup_to_transfer_learn(model, base_model):
"""Freeze all layers and compile the model"""
for layer in base_model.layers:
layer.trainable = False
model.compile(optimizer='rmsprop', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
def add_new_last_layer(base_model, nb_classes):
"""Add last layer to the convnet
Args:
base_model: keras model excluding top
nb_classes: # of classes
Returns:
new keras model with last layer
"""
x = base_model.output
x = GlobalAveragePooling2D()(x)
#x = Dense(FC_SIZE, activation='relu')(x) #new FC layer, random init
predictions = Dense(nb_classes, activation='softmax')(x) #new softmax layer
model = Model(inputs=base_model.input, outputs=predictions)
return model
def train(nb_epoch, batch_size):
"""Use transfer learning and fine-tuning to train a network on a new dataset"""
#nb_train_samples = train_ds.cardinality().numpy()
nb_train_samples=info.splits['train'].num_examples
nb_classes = info.features['label'].num_classes
classes_names = info.features['label'].names
#nb_val_samples = validation_ds.cardinality().numpy()
nb_val_samples = info.splits['validation'].num_examples
#nb_epoch = int(args.nb_epoch)
#batch_size = int(args.batch_size)
def preprocess(features):
#print(features['image'], features['label'])
image = tf.image.resize(features['image'], [224,224])
#image = tf.divide(image, 255)
#print(image)
# data augmentation
image=tf.image.random_flip_left_right(image)
image = preprocess_input(image)
label = features['label']
# for categorical crossentropy
#label = tf.one_hot(label,101,axis=-1)
#return image, tf.cast(label, tf.float32)
return image, label
#pre-processing the dataset to fit a specific image size and 2D labelling
train_generator = train_ds.map(preprocess).batch(batch_size).repeat()
validation_generator = validation_ds.map(preprocess).batch(batch_size).repeat()
#train_generator=train_ds
#validation_generator=validation_ds
#fig = tfds.show_examples(validation_generator, info)
# setup model
base_model = ResNet50(weights='imagenet', include_top=False) #include_top=False excludes final FC layer
model = add_new_last_layer(base_model, nb_classes)
# transfer learning
setup_to_transfer_learn(model, base_model)
history = model.fit(
train_generator,
epochs=nb_epoch,
steps_per_epoch=nb_train_samples//BAT_SIZE,
validation_data=validation_generator,
validation_steps=nb_val_samples//BAT_SIZE)
#class_weight='auto')
#execute
history = train(nb_epoch=NB_EPOCHS, batch_size=BAT_SIZE)
And the performance on food101 dataset:
update 27/11/2020
It's possible to see the discrepancy also in the way smaller oxford_flowers102 dataset:
(train_ds,validation_ds,test_ds),info= tfds.load('oxford_flowers102', split=['train','validation','test'], shuffle_files=True, with_info=True)
Nb: the above plot shows confidences given by running the same training multiple times and evaluatind mean and std to check for the effects on random weights initialization and data augmentation.
Moreover I've tried some hyperparameter tuning on tf2 resulting in the following picture:
changing optimizer (adam and rmsprop)
not applying horizontal flipping aumgentation
deactivating keras resnet50 preprocess_input
Thanks in advance for every suggestion. Here are the accuracy and validation performance on tf1 and tf2 on my dataset:
Update 14/12/2020
I'm sharing the colab for reproducibility on oxford_flowers at the clic of a button:
colab script
I came across something similar, when doing the opposite migration (from TF1+Keras to TF2).
Running this code below:
# using TF2
import numpy as np
from tensorflow.keras.applications.resnet50 import ResNet50
fe = ResNet50(include_top=False, pooling="avg")
out = fe.predict(np.ones((1,224,224,3))).flatten()
sum(out)
>>> 212.3205274187726
# using TF1+Keras
import numpy as np
from keras.applications.resnet50 import ResNet50
fe = ResNet50(include_top=False, pooling="avg")
out = fe.predict(np.ones((1,224,224,3))).flatten()
sum(out)
>>> 187.23898954353717
you can see the same model from the same library on different versions does not return the same value (using sum as a quick check-up). I found the answer to this mysterious behavior in this other SO answer: ResNet model in keras and tf.keras give different output for the same image
Another recommendation I'd give you is, try using pooling from inside applications.resnet50.ResNet50 class, instead of the additional layer in your function, for simplicity, and to remove possible problem-generators :)
I am trying to use hyperopt for a classification deep learning model with keras:
import numpy as np
import tensorflow as tf
import random as rn
# The below is necessary for starting Numpy generated random numbers
# in a well-defined initial state.
np.random.seed(1)
# The below is necessary for starting core Python generated random numbers
# in a well-defined state.
rn.seed(2)
# Force TensorFlow to use single thread.
# Multiple threads are a potential source of non-reproducible results.
session_conf = tf.ConfigProto(intra_op_parallelism_threads=1,
inter_op_parallelism_threads=1)
from keras import backend as K
tf.set_random_seed(2)
sess = tf.Session(graph=tf.get_default_graph(), config=session_conf)
K.set_session(sess)
#importing libraries
import ...
from hyperas import optim
from hyperas.distributions import choice, uniform, randint
from hyperopt import Trials, STATUS_OK, tpe
def data():
return x_train_sequence, y_train, x_test_sequence, y_test
# ===============
# Model creation
# ===============
def create_model(x_train_sequence, y_train, x_test_sequence, y_test):
embedding_dim = {{choice([...])}}
lstm = {{choice([...])}}
num_epochs = {{choice([...])}}
dropout = {{uniform(0, 1)}}
batch_size = {{choice([32])}}
model = Sequential()
model.add(...)
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=["binary_accuracy"])
# Fit the model and evaluate
result = model.fit(x_train_sequence, y_train,
batch_size=batch_size,
validation_data=(x_test_sequence, y_test), verbose=verbose, shuffle=True, epochs=num_epochs)
return {'loss': -validation_acc, 'status': STATUS_OK, 'model': model}
# ===============
# Apply model and find best run
# ===============
if __name__ == '__main__':
best_run, best_model = optim.minimize(model=create_model,
data=data,
algo=tpe.suggest,
rseed=np.random.seed(1),
max_evals=50,
trials=Trials())
X_train, Y_train, X_test, Y_test = data()
print("Evalutation of best performing model:")
print(best_model.evaluate(X_test, Y_test))
print("Best performing model chosen hyper-parameters:")
print(best_run)
Even though I thought I put all the necessary seeds to obtain reproducible cases. I keep getting different results even if I substitute the {{choice([...])}} with integers.
What am I missing? What should I add to seed the model properly?
Thanks so much in advance!
tensorflow.keras api not working on while creating the layers reference, any other methods of creating layers reference?
code :
layer=keras.layers
Error message : NameError: name 'leyer' is not defined
Full code is pasted here...
import tensorflow as tf
from tensorflow import keras
import pandas as pd
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.preprocessing import LabelEncoder
import numpy as np
#makin seed values
seed=7
np.random.seed(seed)
#setting up the dataset for training
dataframe=pd.read_csv("../datasets/iris.csv",header=None)
data=dataframe.values
input_x = data[:,0:4]
true_y = data[:,4]
#Encoding the true_y data to one hot encoding
le=LabelEncoder()
le.fit(true_y)
y_encoded = le.transform(true_y)
y_encoded = keras.utils.to_categorical(y_encoded,num_classes=3)
# creating the model
def base_fun():
layer=keras.layers
model = keras.models.Sequential()
model.add(layer.Dense(4,input_dim=4,kernel_initializer='normal',activation='relu'))
model.add(leyer.Dense(3, kernel_initializer='normal', activation='relu'))
estimator=keras.wrappers.scikit_learn.KerasClassifier(build_fn=base_fun,epochs=20,batch_size=10)
kfold = KFold(n_splits=10, shuffle=True, random_state=seed)
result = cross_val_score(estimator, input_x, y_encoded,cv=kfold)
print("Accuracy : %.2%% (%.2%%)" %(result.mean()*100, result.std()*100))
Well, this line:
model.add(leyer.Dnese(3, kernel_initializer='normal', activation='relu'))
has two typos, namely leyer should be layer and Dnese should be Dense like
model.add(layer.Dense(3, kernel_initializer='normal', activation='relu'))
Based on your comment, this line also causes an error:
estimator = keras.wrappers.scikit_learn.KerasClassifier( build_fn = base_fun, epochs = 20, batch_size = 10 )
From the Keras Scikit documentation:
build_fn should construct, compile and return a Keras model, which will then be used to fit/predict.
But you function base_fun() does not return anything. Append this line at the end of base_fun():
return model
As per your comment, the last print line could be changed to this (I don't know the % formatting, I generally use the syntax below):
print( "Accuracy : {:.2%} ({:.2%})".format( result.mean(), result.std() ) )
I'm trying to do a small test with my dataset on Keras Regressor (using TensorFlow), but I'm having a small issue. The error seems to be on the function cross_val_score from scikit. It starts on it and the last error message is:
File "/usr/local/lib/python2.7/dist-packages/Keras-2.0.2-py2.7.egg/keras/backend/tensorflow_backend.py", line 298, in _initialize_variables
variables = tf.global_variables()
AttributeError: 'module' object has no attribute 'global_variables'
My full code is basically the example found in http://machinelearningmastery.com/regression-tutorial-keras-deep-learning-library-python/ with small changes.
I've looked upon the " 'module' object has no attribute 'global_variables' " error and it seems to be about the Tensorflow version, but I'm using the most recent one (1.0) and there is no function in the code that works directly with tf that I can change. Below is my full code, is there anyway i can change it so it works? Thanks for the help
import numpy
import pandas
import sys
from keras.models import Sequential
from keras.layers import Dense
from keras.wrappers.scikit_learn import KerasRegressor
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import KFold
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
from sklearn.datasets import load_svmlight_file
# define base mode
def baseline_model():
# create model
model = Sequential()
model.add(Dense(68, activation="relu", kernel_initializer="normal", input_dim=68))
model.add(Dense(1, kernel_initializer="normal"))
# Compile model
model.compile(loss='mean_squared_error', optimizer='adam')
return model
X, y, query_id = load_svmlight_file(str(sys.argv[1]), query_id=True)
scaler = StandardScaler()
X = scaler.fit_transform(X.toarray())
# fix random seed for reproducibility
seed = 1
numpy.random.seed(seed)
# evaluate model with standardized dataset
estimator = KerasRegressor(build_fn=baseline_model, nb_epoch=100, batch_size=5, verbose=0)
kfold = KFold(n_splits=5, random_state=seed)
results = cross_val_score(estimator, X, y, cv=kfold)
print("Results: %.2f (%.2f) MSE" % (results.mean(), results.std()))
You are probably using an older Tensorflow version install tensorflow 1.2.0rc2 and you should be fine.