I've got myself into a bit of trouble. I've got 4 features, and I want to predict each one of them at the same time. My lookback is 12 and I want to predict 12 timesteps ahead. Is it possible to predict all the 4 targets in parallel?
I have to following piece of code. Shape on train_df is (40000, 4) and val_df is (8000, 4).
win_length=12
batch=32
n_features=4
train_generator = TimeseriesGenerator(train_df, train_df, length=win_length, sampling_rate=1, batch_size=batch)
val_generator = TimeseriesGenerator(val_df, val_df, length=win_length, sampling_rate=1, batch_size=batch)
model = Sequential()
model.add(LSTM(128, activation='tanh', input_shape=(win_length, n_features), return_sequences=True))
model.add(LSTM(128, activation='tanh', return_sequences=True))
model.add(LSTM(64, activation='tanh', return_sequences=True))
model.add(TimeDistributed(Dense(1)))
model.compile(loss='mse', optimizer='adam')
model.summary()
model.fit_generator(train_generator, validation_data=val_generator)
I get the following error from the fit_generator-function, and I can't seem to figure out how so. Any ideas?
tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [32,12] vs. [32,4]
I don't quite understand how TimeseriesGenerator works, but it seems like you want to have two same sequences for data and target, hence the mse. I've checked myself and TimeseriesGenerator doesn't produce two same sequences (data with shape (32, 12, 4) and targets with shape (32, 4)). My best bet right now is to implement the generator manually. Also I think model.add(TimeDistributed(Dense(1))) should be changed to model.add(TimeDistributed(Dense(4)))
Related
I need outputs at every recurrent layer and my setup is as follows:
100 training examples, 3 time steps per example, and 20-d feature vector for each individual element.
x_train: (100,3,20)
y_train: (100,20)
LSTM architecture:
model.add(LSTM(20, input_shape=(3,20), return_sequences=True))
model.compile(loss='mean_absolute_error', optimizer='adam', metrics=['accuracy'])
model.summary()
Training:
history = model.fit(x_train, y_train, epochs=50, validation_data=(x_test, y_test))
Error:
ValueError: Dimensions must be equal, but are 20 and 3 for '{{node Equal}} = Equal[T=DT_FLOAT, incompatible_shape_error=true](IteratorGetNext:1, Cast_1)' with input shapes: [?,20], [?,3].
Please help me with the correct input/output LSTM dimensions.
Thanks
LSTM(20, input_shape=(3,20), return_sequences=True) takes as input shape (100,3,20) and returns (100,3,20). Your target output is however encoded as (100,20).
From the dimensions, I assume you want to map each sequence to a non-sequence, i.e. you can do:
LSTM(20, input_shape=(3,20), return_sequences=False)
This will return the final hidden state, i.e. a shape of (100,20) which matches your target output.
I am trying to create a neural network with keras that will have as input N multivariate time-series and as target output N time-series. I converted the time-series to a supervised problem with the window or lag method. As input I have a 4D matrix (samples, variables, sequence, lag) and as output a 2D matrix (samples, sequence). I found similar examples that used CNN+LSTM models, but I have difficulties applying them. In case it helps, I have train_X, train_y, test_X, test_y with dimensions (112, 5, 7998, 2) (112, 7998) (29, 5, 7998, 2) (29, 7998)
I have tried applying and removing the TimeDistributed Keras wrapper to the CNN part only and the whole model. The relevant part of the code is bellow.
model = Sequential()
model.add(TimeDistributed(Conv2D(filters=32, kernel_size=(1, 80), activation='relu', padding='same', input_shape=(train_X.shape[1], train_X.shape[2], train_X.shape[3]))))
model.add(TimeDistributed(MaxPool2D(pool_size=(1, 2),strides=1)))
model.add(TimeDistributed(Dropout(0.5)))
model.add(TimeDistributed(Flatten()))
model.add(TimeDistributed(LSTM(100, return_sequences=True)))
model.add(TimeDistributed(Dropout(0.2)))
model.add(TimeDistributed(Dense(units=1)))
model.compile(loss='mean_squared_error', optimizer='adam')
I get an index error.
IndexError: list index out of range
I am trying to implement a 5 class animal classifier using Keras. I am building the CNN from scratch and the weird thing is, the validation accuracy stays constant at 0.20 for all epochs. Any idea why this is happening? The dataset folder contains train, test and validation folders. And each of the folders contains 5 folders corresponding to the 5 classes. What am I doing wrong?
I have tried multiple optimizer but the problem persists. I have included the code sample below.
import warnings
warnings.filterwarnings("ignore")
#First convolution layer
model = Sequential()
model.add(Conv2D(filters=32, kernel_size=(3, 3), activation='relu',kernel_initializer='he_normal',input_shape=input_shape))
model.add(MaxPooling2D(pool_size=(2, 2)))
#Second convolution layer
model.add(Conv2D(filters=64, kernel_size=(3, 3), activation='relu',kernel_initializer='he_normal',input_shape=input_shape))
model.add(MaxPooling2D(pool_size=(2, 2)))
#Flatten the outputs of the convolution layer into a 1D contigious array
model.add(Flatten())
#Add a fully connected layer containing 256 neurons
model.add(Dense(256, activation='relu',kernel_initializer='he_normal'))
model.add(BatchNormalization())
#Add another fully connected layer containing 256 neurons
model.add(Dense(256, activation='relu',kernel_initializer='he_normal'))
model.add(BatchNormalization())
#Add the ouput layer containing 5 neurons, because we have 5 categories
model.add(Dense(5, activation='softmax',kernel_initializer='glorot_uniform'))
optim=RMSprop(lr=1e-6)
model.compile(loss='categorical_crossentropy',optimizer=optim,metrics=['accuracy'])
model.summary()
#We will use the below code snippet for rescaling the images to 0-1 for all the train and test images
train_datagen = ImageDataGenerator(rescale=1./255)
#We won't augment the test data. We will just use ImageDataGenerator to rescale the images.
test_datagen = ImageDataGenerator(rescale=1./255)
train_generator = train_datagen.flow_from_directory(train_data_dir,
classes=['frog', 'giraffe', 'horse', 'tiger','dog'],
target_size=(img_width, img_height),
batch_size=batch_size,
class_mode='categorical',
shuffle=False)
validation_generator = test_datagen.flow_from_directory(validation_data_dir,
classes=['frog', 'giraffe', 'horse', 'tiger','dog'],
target_size=(img_width, img_height),
batch_size=batch_size,
class_mode='categorical',
shuffle=False)
hist=History()
model.fit_generator(train_generator,
steps_per_epoch=nb_train_samples // batch_size,
epochs=epochs,
validation_data=validation_generator,
validation_steps=nb_validation_samples // batch_size,
callbacks=[hist])
model.save('models/basic_cnn_from_scratch_model.h5') #Save the model weights #Load using: model = load_model('cnn_from_scratch_weights.h5') from keras.models import load_model
print("Time taken to train the baseline model from scratch: ",datetime.now()-global_start)
Check the following for your data:
Shuffle the training data well (I see shuffle=False everywhere)
Properly normalize all data (I see you are doing rescale=1./255, maybe okay)
Proper train/val split (you seem to be doing that too)
Suggestions for your model:
Use multiple Conv2D layers followed by a final Dense. That's what works best for image classification problems. You can also look at popular architectures that are tried and tested; e.g. AlexNet
Can change the optimizer to Adam and try with different learning rates
Have a look at your training and validation loss graphs and see if they look as expected
Also, I guess you corrected the shape of the 2nd Conv2D layer as mentioned in the comments.
It looks as if your output is always the same animal, thus you have a 20% accuracy. I highly recommend you to check your testing outputs to see if they are all the same.
Also you said that you were building a CNN but in the code snipet you posted I see only dense layers, it is going to be hard for a dense architecture to do this task, and it is very small. What is the size of your pictures?
Hope it helps!
The models seems to be working now. I have removed shuffle=False attribute. Corrected the input shape for the 2nd convolution layer. Changed the optimizer to adam. I have reached a validation accuracy of almost 94%. However, I have not yet tested the model on unseen data. There is a bit of overfitting in the model. I will have to use some aggressive dropouts to reduce them. Thanks!
I don't understand input of RNN model. Why it show None before node size every layer. Why it is (None,1) (None,12)
This is my code.
K.clear_session()
model = Sequential()
model.add(Dense(12, input_dim=1, activation='relu'))
model.add(Dropout(0.2))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam')
model.summary()
This is not a RNN, it's just a fully connected network (FC or Dense).
The first dimension of every tensor in a Keras network is the batch_size, which represents the number of "samples" or "examples" you are passing to the model. The value is None because this dimension is not fixed, you can have batches of any size you want.
Trying to add validation to model.fit, but whenever I do I get an error:
ValueError: Cannot feed value of shape (6, 4, 10) for Tensor 'lstm_input_1:0', which has shape '(32, 4, 10)'
Model:
data_dim = 10
timesteps = 4
batch_size = 32
model = Sequential()
model.add(LSTM(128, batch_input_shape=(batch_size, timesteps, data_dim), return_sequences=True, stateful=True))
model.add(LSTM(64, return_sequences=True, stateful=True))
model.add(LSTM(32, stateful=True))
model.add(Dense(2, activation='softmax'))
sgd = SGD(lr=0.001, momentum=0.0, decay=0.0, nesterov=False)
model.compile(optimizer=sgd, loss='categorical_crossentropy', metrics=['accuracy'])
model.fit(x_train, y_train, nb_epoch=50, batch_size=batch_size, validation_split=0.5)
What could be the error? If I remove validation_split the training works just fine. I've also tried to manually split my training set into two and add it with validation_data=(x_val, y_val) but I got the exact same error.
The issue comes from the fact that you hard code the batch_size value of your inputs. You have fixed it to 32 and then when you try and validate your model, the validation data is sent with a batch of 6 samples, this might be because you don't have enough validation data or maybe because the number of sample isn't a multiple of 32... However, I would let the batch_size free if I was you. Like this:
model.add(LSTM(128, input_shape=(timesteps, data_dim), return_sequences=True, stateful=True))
You specify input_shape instead of batch_input_shape. That way, your network will accept any size of batch, every layer down in the stream of your model are made to adapt to any batch_size if not hardcoded.
I hope this helps :)