I am trying to do gridsearch using scikit-learn GridSearchCV and KerasClassifier for a multilabel classification problem having 346 labels. I am trying to evaluate the models based on a custom metric. But I am always running into the following error. My training data size is 5334.
ValueError: operands could not be broadcast together with shapes (5334,346) (5334,)
def my_custom_scorer(y_true,y_pred):
true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
possible_positives = K.sum(K.round(K.clip(y_true, 0, 1)))
recall = true_positives / (possible_positives + K.epsilon())
return recall
custom_scorer = make_scorer(my_custom_scorer, greater_is_better=True)
def create_model(learn_rate = 0.01):
# create model
model = Sequential()
model.add(Dense(100, activation = 'sigmoid',input_dim=4))
model.add(Dense(346, activation='sigmoid'))
# Compile model
optimizer = SGD(lr=learn_rate, momentum=0)
model.compile(optimizer=optimizer,
loss=custom_loss(weights),
metrics=['accuracy'])
return model
model = KerasClassifier(build_fn=create_model,verbose=0)
learn_rate = [0.001, 0.01, 0.1]
batch_size = [10]
epochs = [1]
param_grid = dict(epochs=epochs,batch_size=batch_size,learn_rate=learn_rate)
grid = GridSearchCV(estimator=model,
param_grid=param_grid,n_jobs=1,scoring=custom_scorer)
grid_result = grid.fit(X_train, Y_train)
print("Best: %f using %s" % (grid_result.best_score_,
grid_result.best_params_))
means = grid_result.cv_results_['mean_test_score']
stds = grid_result.cv_results_['std_test_score']
params = grid_result.cv_results_['params']
for mean, stdev, param in zip(means, stds, params):
print("%f (%f) with: %r" % (mean, stdev, param))
Related
I'm newbie in Neural Network. I'm going to do a text classification research using MLP model with keras. Input layer consisting of 900 nodes, 2 hidden layers, and 2 outputs.
The code I use is as follows:
#Split data training & testing (90:10)
Train_X, Test_X, Train_Y, Test_Y = model_selection.train_test_split(dataset['review'],dataset['sentimen'],test_size=0.2, random_state=8)
Encoder = LabelEncoder()
Train_Y = Encoder.fit_transform(Train_Y)
Test_Y = Encoder.fit_transform(Test_Y)
Tfidf_vect = TfidfVectorizer(max_features=None)
Tfidf_vect.fit(dataset['review'])
Train_X_Tfidf = Tfidf_vect.transform(Train_X)
Test_X_Tfidf = Tfidf_vect.transform(Test_X)
#ANN Architecture
model = Sequential()
model.add(Dense(units = 100, activation = 'sigmoid', input_shape=(32, 900)))
model.add(Dense(units = 100, activation = 'sigmoid'))
model.add(Dense(units = 2, activation = 'sigmoid'))
opt = Adam (learning_rate=0.001)
model.compile(loss = 'binary_crossentropy', optimizer = opt,
metrics = ['accuracy'])
print(model.summary())
#Hyperparameter
epochs= 100
batch_size= 32
es = EarlyStopping(monitor="val_loss",mode='min',patience=10)
model_prediction = model.fit(Train_X_Tfidf, Train_Y, epochs=epochs,
batch_size=batch_size, verbose=1,
validation_split=0.1, callbacks =[es])
But getting Error:
/usr/local/lib/python3.8/dist-packages/keras/engine/data_adapter.py in train_validation_split(arrays, validation_split)
1478 unsplitable = [type(t) for t in flat_arrays if not _can_split(t)]
1479 if unsplitable:
-> 1480 raise ValueError(
1481 "`validation_split` is only supported for Tensors or NumPy "
1482 "arrays, found following types in the input: {}".format(unsplitable))
ValueError: `validation_split` is only supported for Tensors or NumPy arrays, found following types in the input: [<class 'scipy.sparse.csr.csr_matrix'>]
How to Fix it? Thank you so much.
i have a problem with gridsearch keras problem which loops every time with the same epoch = 25? It doesn't change to 35.
def build_classifier(optimizer):
classifier = Sequential()
classifier.add(Dense(units = 3000, kernel_initializer = 'uniform', activation = 'relu', input_dim = pca_dimensions))
classifier.add(Dense(units = 3000, kernel_initializer = 'uniform', activation = 'relu'))
classifier.add(Dense(units = 1, kernel_initializer = 'uniform', activation = 'sigmoid'))
classifier.compile(optimizer = optimizer, loss = 'binary_crossentropy', metrics = ['accuracy'])
return classifier
classifier = KerasClassifier(build_fn = build_classifier)
parameters = {'batch_size': [1000],
'epochs': [25,35,45],
'optimizer': ['adam']}
grid_search = GridSearchCV(estimator = classifier,
param_grid = parameters,
scoring = 'accuracy',
cv = 10)enter code here
grid_results = grid_search.fit(X_train, y_train)
print("Best: %f using %s" % (grid_results.best_score_, grid_results.best_params_))
means = grid_results.cv_results_['mean_test_score']
stds = grid_results.cv_results_['std_test_score']
params = grid_results.cv_results_['params']
for mean, stdev, param in zip(means, stds, params):
print("%f (%f) with: %r" % (mean, stdev, param))
I am using Python 3.7.5 and TensorFlow 2.0's 'GradientTape' API for classification of MNIST dataset using 300 100 dense fully connected architecture. I would like to use TensorFlow's 'EarlyStopping' with GradientTape() so that the training stops according to the variable being watched or monitored and according to patience parameters.
The code I have is below:
# Use tf.data to batch and shuffle the dataset
train_ds = tf.data.Dataset.from_tensor_slices((X_train, y_train)).shuffle(100).batch(batch_size)
test_ds = tf.data.Dataset.from_tensor_slices((X_test, y_test)).batch(batch_size)
# Choose an optimizer and loss function for training-
loss_fn = tf.keras.losses.BinaryCrossentropy()
optimizer = tf.keras.optimizers.Adam(lr = 0.001)
def create_nn_gradienttape():
"""
Function to create neural network for use
with GradientTape API following MNIST
300 100 architecture
"""
model = Sequential()
model.add(
Dense(
units = 300, activation = 'relu',
kernel_initializer = tf.keras.initializers.GlorotNormal,
input_shape = (784,)
)
)
model.add(
Dense(
units = 100, activation = 'relu',
kernel_initializer = tf.keras.initializers.GlorotNormal
)
)
model.add(
Dense(
units = 10, activation = 'softmax'
)
)
return model
# Instantiate the model to be trained using GradientTape-
model = create_nn_gradienttape()
# Select metrics to measure the error & accuracy of model.
# These metrics accumulate the values over epochs and then
# print the overall result-
train_loss = tf.keras.metrics.Mean(name = 'train_loss')
train_accuracy = tf.keras.metrics.BinaryAccuracy(name = 'train_accuracy')
test_loss = tf.keras.metrics.Mean(name = 'test_loss')
test_accuracy = tf.keras.metrics.BinaryAccuracy(name = 'train_accuracy')
# Use tf.GradientTape to train the model-
#tf.function
def train_step(data, labels):
"""
Function to perform one step of Gradient
Descent optimization
"""
with tf.GradientTape() as tape:
# 'training=True' is only needed if there are layers with different
# behavior during training versus inference (e.g. Dropout).
# predictions = model(data, training=True)
predictions = model(data)
loss = loss_fn(labels, predictions)
# 'gradients' is a list variable!
gradients = tape.gradient(loss, model.trainable_variables)
# IMPORTANT:
# Multiply mask with computed gradients-
# List to hold element-wise multiplication between-
# computed gradient and masks-
grad_mask_mul = []
# Perform element-wise multiplication between computed gradients and masks-
for grad_layer, mask in zip(gradients, mask_model_stripped.trainable_weights):
grad_mask_mul.append(tf.math.multiply(grad_layer, mask))
# optimizer.apply_gradients(zip(gradients, model.trainable_variables))
optimizer.apply_gradients(zip(grad_mask_mul, model.trainable_variables))
train_loss(loss)
train_accuracy(labels, predictions)
#tf.function
def test_step(data, labels):
"""
Function to test model performance
on testing dataset
"""
# training=False is only needed if there are layers with different
# behavior during training versus inference (e.g. Dropout).
predictions = model(data)
t_loss = loss_fn(labels, predictions)
test_loss(t_loss)
test_accuracy(labels, predictions)
EPOCHS = 15
for epoch in range(EPOCHS):
# Reset the metrics at the start of the next epoch
train_loss.reset_states()
train_accuracy.reset_states()
test_loss.reset_states()
test_accuracy.reset_states()
for x, y in train_ds:
train_step(x, y)
for x_t, y_t in test_ds:
test_step(x_t, y_t)
template = 'Epoch {0}, Loss: {1:.4f}, Accuracy: {2:.4f}, Test Loss: {3:.4f}, Test Accuracy: {4:4f}'
print(template.format(epoch + 1,
train_loss.result(), train_accuracy.result()*100,
test_loss.result(), test_accuracy.result()*100))
# Count number of non-zero parameters in each layer and in total-
# print("layer-wise manner model, number of nonzero parameters in each layer are: \n")
model_sum_params = 0
for layer in model.trainable_weights:
# print(tf.math.count_nonzero(layer, axis = None).numpy())
model_sum_params += tf.math.count_nonzero(layer, axis = None).numpy()
print("Total number of trainable parameters = {0}\n".format(model_sum_params))
In the code above, How can I use 'tf.keras.callbacks.EarlyStopping' with GradientTape() API ?
Thanks!
I am attempting to wrap my keras models in scikit learn GridSearchCV and Pipeline structures for hyperparameter tuning.
It works absolutely fine when the build_fn function takes 0 arguments for use in KerasClassifier. However it fails whenever I use a function which takes arguments.
Example code below
def prepare_classifier(x, y):
shape_of_input = x.shape
shape_of_target = y.shape
classifier = Sequential()
## number of neurons = 30
## kernel_initializer determines how the weights are initialized
## activation is the activation function at this particular hidden layer
## input_shape is the number of features in a single row.. in this case it is shape_of_input[1]
## shape_of_input[0] is the total number of such rows
classifier.add(Dense(units = 30, activation = 'relu', kernel_initializer = 'uniform', input_dim = shape_of_input[1]))
classifier.add(Dense(units = 30, activation = 'relu', kernel_initializer = 'uniform'))
## we are predicting 10 digits for each row of x.
## in total there are shape_of_input[0] rows in total
classifier.add(Dense(10, activation = 'softmax'))
## categorical_crossentropy is the loss function for multi output loss function
classifier.compile(optimizer = 'adam', loss = 'categorical_crossentropy', metrics = ['accuracy'])
return classifier
def fit(classifier, x_train, y_train, epoch_size, batch_size = 10):
pipeline = Pipeline([
('keras_classifier', classifier)
])
param_grid = {
'keras_classifier__batch_size' : [10,20,30,50],
'keras_classifier__epochs' : [100, 200, 300],
'keras_classifier__x' : [x_train],
'keras_classifier__y' : [y_train],
}
grid = GridSearchCV(estimator = pipeline, param_grid = param_grid, n_jobs = -1)
grid.fit(x_train, y_train)
print("Best parameters are : ", grid.best_params_, '\n grid best score :', grid.best_score_)
classifier = KerasClassifier(build_fn = prepare_classifier, x = x_train[0:100], y = y_train )
fit(classifier, x_train[:100], y_train, epoch_size )
This is for some x, and some y data (p.s. I have used mnist data)
The error I get is :
RuntimeError: Cannot clone object , as the constructor either does not set or modifies parameter x
However if my prepare_classifier function takes no arguments code works absolutely fine.
What am I doing incorrectly?
solved it. essentially the below line was the issue
classifier = KerasClassifier(build_fn = prepare_classifier, x = x_train[0:100], y = y_train )
needed to be changed to
classifier = KerasClassifier(build_fn = prepare_classifier)
and the parameters for the prepare_classifier needs to be sent using param_grid
I am trying to use GridSearchCV along with KerasRegressor for hyperparameter search. Keras model.fit function on its own allows to look at the 'loss' and 'val_loss' variables using the history object.
Is it possible to look at the 'loss' and 'val_loss' variables when using GridSearchCV.
Here is the code i am using to do a gridsearch:
model = KerasRegressor(build_fn=create_model_gridsearch, verbose=0)
layers = [[16], [16,8]]
activations = ['relu' ]
optimizers = ['Adam']
param_grid = dict(layers=layers, activation=activations, input_dim=[X_train.shape[1]], output_dim=[Y_train.shape[1]], batch_size=specified_batch_size, epochs=num_of_epochs, optimizer=optimizers)
grid = GridSearchCV(estimator=model, param_grid=param_grid, scoring='neg_mean_squared_error', n_jobs=-1, verbose=1, cv=7)
grid_result = grid.fit(X_train, Y_train)
# summarize results
print("Best: %f using %s" % (grid_result.best_score_, grid_result.best_params_))
means = grid_result.cv_results_['mean_test_score']
stds = grid_result.cv_results_['std_test_score']
params = grid_result.cv_results_['params']
for mean, stdev, param in sorted(zip(means, stds, params), key=lambda x: x[0]):
print("%f (%f) with: %r" % (mean, stdev, param))
def create_model_gridsearch(input_dim, output_dim, layers, activation, optimizer):
model = Sequential()
for i, nodes in enumerate(layers):
if i == 0:
model.add(Dense(nodes, input_dim=input_dim))
model.add(Activation(activation))
else:
model.add(Dense(nodes))
model.add(Activation(activation))
model.add(Dense(output_dim, activation='linear'))
model.compile(optimizer=optimizer, loss='mean_squared_error')
return model
How can i get the training and CV loss per epoch for the best model, grid_result.best_estimator_.model?
There is no variable like grid_result.best_estimator_.model.history.keys()
The history is well hidden. I was able to find it in
grid_result.best_estimator_.model.model.history.history
There is slight change in above answer.
"grid_result.best_estimator_.model.history.history" will give history object.