I am trying to apply a CNN on my numerical dataset from a CSV file, but I have problems with the dimensions. My Dataset consists of 26 Features/Columns and 1200 rows/samples. The dataset has 3 labels.
Dataset = pd.read_csv("...", header=0)
features = ['...']
x = Dataset [features]
y = Dataset .Classifier
sc = PowerTransformer()
x = sc.fit_transform(x)
x_train, x_test, y_train, y_test = train_test_split(x, y, train_size=0.75)
y_train = to_categorical(y_train)
y_test = to_categorical(y_test)
model = Sequential()
model.add(Conv1D(filters=64, kernel_size=3, activation='relu'))
model.add(MaxPooling1D(pool_size=4))
model.add(LSTM(64))
model.add(Dense(3, activation='softmax'))
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
model.fit(x_train, y_train, epochs=100, batch_size=8, verbose=1)
accuracy = model.evaluate(x_test, y_test)
print(accuracy)
I get the following error:
ValueError: Error when checking input: expected conv1d_1_input to have 3 dimensions, but got array with shape (900, 26)
I am not sure how to reshape the data. As far as I know I only need a vector.
You are partly correct. You do need a vector, but it has to be of different dimensions.
Conv1D layer takes as input:
Input shape:
3+D tensor with shape: batch_shape + (steps, input_dim)
In the model.fit function you set your batch size to 8. This means that you have to give sets of 8 samples per step (step = iteration before the network weights are updated).
What you have to do is generate sets (or batches) of 8 samples and then feed them to your network.
Related
I found this paper they present Convolutional Neural Network can get the best accuracy for non-image classify. So, I want to use CNN with non-image dataset. I download Early Stage Diabetes Risk Prediction Dataset form kaggle. I create CNN moldel like this code.
dataset = loadtxt('diabetes_data_upload.csv', delimiter=',')
# split into input (X) and output (y) variables
X = dataset[:,0:16]
Y = dataset[:,16]
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.3)
model = Sequential()
model.add(Conv1D(16,2, activation='relu', input_shape=(16, 1)))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
model.fit(X_train, y_train, epochs=100, batch_size=10)
It show error like this.
ValueError: `logits` and `labels` must have the same shape, received ((None, 15, 1) vs (None,)).
How to fix it ?
You can use tf.keras.layers.Flatten(). Something like below can solve youe problem.
from sklearn.model_selection import train_test_split
import tensorflow as tf
import numpy as np
X = np.random.rand(100, 16)
Y = np.random.randint(0,2, size = 100) # <- Because you have two labels, I generate ranom 0,1
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.3)
model = tf.keras.Sequential()
model.add(tf.keras.layers.Conv1D(16,2, activation='relu', input_shape=(16, 1)))
model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
model.fit(X_train, y_train, epochs=1, batch_size=10)
Update by thanks Ameya, we can solve this problem by only using tf.keras.layers.GlobalAveragePooling1D() too.
(by thanks Djinn and his_comment, but consider: these are two different approaches that do different things. Flatten() preserves all data, and just converts input tensors to a 1D tensor BUT GlobalAveragePooling1D() tries to generalize and loses data. Pooling layers with non-image data can significantly affect performance but I've noticed AveragePooling does the least "damage,")
model = tf.keras.Sequential()
model.add(tf.keras.layers.Conv1D(16,2, activation='relu', input_shape=(16, 1)))
model.add(tf.keras.layers.GlobalAveragePooling1D())
model.add(tf.keras.layers.Dense(1, activation='sigmoid'))
7/7 [==============================] - 0s 2ms/step - loss: 0.6954 - accuracy: 0.0000e+00
I am trying to predict the output of a function. (Eventually it will be multi input multi output) but for now just to get the mechanics right I am trying to predict the output of sin function. My dataset is as follows,
t0 t1
0 0.000000 0.125333
1 0.125333 0.248690
2 0.248690 0.368125
3 0.368125 0.481754
4 0.481754 0.587785
5 0.587785 0.684547
6 0.684547 0.770513
7 0.770513 0.844328
8 0.844328 0.904827
9 0.904827 0.951057
.....
Total of 100 values. t0 is the current input t1 is the next output I want to predict. Then data is split into train/test via scikit,
x_train, x_test, y_train, y_test = train_test_split(wave["t0"].values, wave["t1"].values, test_size=0.20)
Problem happens in fit, I get an error that says input wrong dimensions.
model = Sequential()
model.add(LSTM(128, input_shape=??? ,stateful=True))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam')
model.fit(x_train, y_train,
batch_size=10, epochs=100,
validation_data=(x_test, y_test))
I've tried other questions on the site to fix the problem but no matter what i try i can not get keras to recognize correct input.
The LSTM expects the input data to be of shape (batch_size, time_steps, num_features). In sine-wave prediction, the num_features is 1, the time_steps is how many previous time-points the LSTM should use for prediction. In the example below, batch size is 1, time_steps is 2 and num_features is 1.
x_train = np.ones((1,2,1))
y_train = np.ones((1,1))
x_test = np.ones((1,2,1))
y_test = np.ones((1,1))
model = Sequential()
model.add(LSTM(128, input_shape=(2,1)))
#for stateful
#model.add(LSTM(128, batch_input_shape=(1,2,1), stateful=True))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam')
model.fit(x_train, y_train,
batch_size=1, epochs=100,
validation_data=(x_test, y_test))
I have a problem with data shape in RNN model.
y_pred = model.predict(X_test_re) # X_test_re.shape (35,1,1)
It returned an error like below.
ValueError: In a stateful network, you should only pass inputs with a number of samples that can be divided by the batch size. Found: 35 samples. Batch size: 32.
first Question
I can't understand because I defined batch_size=10, but why error msg says batch size:32?
Second Question
when I modified the code as below
model.predict(X_test_re[:32])
I also got an error msg but I don't know what it means.
InvalidArgumentError: Incompatible shapes: [32,20] vs. [10,20]
[[{{node lstm_1/while/add_1}}]]
I built a model and fit it as below.
features = 1
timesteps = 1
batch_size = 10
K.clear_session()
model=Sequential()
model.add(LSTM(20, return_sequences=True, stateful=True,
batch_input_shape=(batch_size, timesteps, features)))
model.add(LSTM(20, stateful=True))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam')
model.summary()
earyl_stop = EarlyStopping(monitor='val_loss', patience=5, verbose=1)
hist = model.fit(X_train_re, y_train, # X_train_re.shape (70,1,1), y_train(70,)
batch_size=batch_size,
epochs=100,
verbose=1,
shuffle=False,
callbacks=[earyl_stop])
Until fit model, it works without any problem.
+) source code
first, df looks like,
# split_train_test from dataframe
train,test = df[:-35],df[-35:]
# print(train.shape, test.shape) (70, 2) (35, 2)
# scaling
sc = MinMaxScaler(feature_range=(-1,1))
train_sc = sc.fit_transform(train)
test_sc = sc.transform(test)
# Split X,y (column t-1 is X)
X_train, X_test, y_train, y_test = train_sc[:,1], test_sc[:,1], train_sc[:,0], test_sc[:,0]
# reshape X_train
X_train_re = X_train.reshape(X_train.shape[0],1,1)
X_test_re = X_test.reshape(X_test.shape[0],1,1)
I have received multiple diffrent ValueErrors when trying to solve following by changing many parameters.
It is a time series problem, I have data from 60 shops, 215 items, 1034 days. I have splitted 973 days for train and 61 for test.:
train_x = train_x.reshape((60, 973, 215))
test_x = test_x.reshape((60, 61, 215))
train_y = train_y.reshape((60, 973, 215))
test_y = test_y.reshape((60, 61, 215))
My model:
model = Sequential()
model.add(LSTM(100, input_shape=(train_x.shape[1], train_x.shape[2]),
return_sequences='true'))
model.add(Dense(215))
model.compile(loss='mean_squared_error', optimizer='adam', metrics=
['accuracy'])
history = model.fit(train_x, train_y, epochs=10,
validation_data=(test_x, test_y), verbose=2, shuffle=False)
ValueError: Error when checking input: expected lstm_1_input to have
shape (973, 215) but got array with shape (61, 215)
You've split your data with respect to timesteps as opposed to the samples. You need to decide on what are your samples in the first instance. For the sake of the answer I will assume these are along the first axis (assuming the data has been framed as a supervised time-series problem).
The input_size in LSTM expects the shape of (timesteps, data_dim) as explained here, and these dimensions must remain the same for each batch. In your example, samples from training and testing have different dimensions. The batch size can differ (unless specified with batch_size parameter).
Your data should be split between training and testing along the first axis. Here is an analogous example from Keras tutorials:
from keras.models import Sequential
from keras.layers import LSTM, Dense
import numpy as np
data_dim = 16
timesteps = 8
num_classes = 10
# expected input data shape: (batch_size, timesteps, data_dim)
model = Sequential()
model.add(LSTM(32, return_sequences=True,
input_shape=(timesteps, data_dim))) # returns a sequence of vectors of dimension 32
model.add(LSTM(32, return_sequences=True)) # returns a sequence of vectors of dimension 32
model.add(LSTM(32)) # return a single vector of dimension 32
model.add(Dense(10, activation='softmax'))
model.compile(loss='categorical_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
# Generate dummy training data
x_train = np.random.random((1000, timesteps, data_dim))
y_train = np.random.random((1000, num_classes))
# Generate dummy validation data
x_val = np.random.random((100, timesteps, data_dim))
y_val = np.random.random((100, num_classes))
model.fit(x_train, y_train,
batch_size=64, epochs=5,
validation_data=(x_val, y_val))
You will notice that timesteps is the same for training and testing data and x_train.shape[1] == x_val.shape[1]. It is the number of samples that differs along the first axis x_train.shape[0] is 1000 and x_val.shape[0] is 100.
I have features in shape of (size,2) and labels in shape of (size,1) i.e. for [x,y] in feature the label will be z. I want to build an LSTM in keras that can do such job since the feature is linked somehow with the previous inputs i.e. 1 or multiple(I believe its a hyperparameter).
Sample dataset values are:-
features labels
[1,2] [5]
[3,4] [84]
Here is what I have done so far:-
print(labels.shape) #prints (1414,2)
print(features.shape) #prints(1414,1)
look_back=2
# reshape input to be [samples, time steps, features]
features = np.reshape(features, (features.shape[0], 1, features.shape[1]))
labels = np.reshape(labels, (labels.shape[0], 1, 1))
X_train, X_test, y_train, y_test = train_test_split(features,labels,test_size=0.2)
model = Sequential()
model.add(LSTM(4, input_shape=(1, look_back))) #executing correctly
model.add(Dense(1)) #error here is "ValueError: Error when checking target: expected dense_1 to have 2 dimensions, but got array with shape (1131, 1, 1)"
model.summary()
model.compile(loss='mean_squared_error', optimizer='adam')
model.fit(X_train, y_train, epochs=100, batch_size=1, verbose=2)
So can anyone please help me build a minimal LSTM example to run my code? Thank you. I don't know how can dense layer have 2 dimensions I mean it is an integer telling how many units to use in the dense layer.
You must not reshape your labels.
Try this:
features = np.reshape(features, (features.shape[0], 1, features.shape[1]))
model = Sequential()
model.add(LSTM(4, input_shape=(1, features.shape[1])))
model.add(Dense(1))
model.summary()
model.compile(loss='mean_squared_error', optimizer='adam')
model.fit(X_train, y_train, epochs=100, batch_size=1, verbose=2)