This my script:
from tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint
model = Sequential()
model.add(Embedding(vocab_size, embedding_dim, input_length=train_padded.shape[1]))
model.add(Conv1D(48, 5, activation='relu', padding='valid'))
model.add(GlobalMaxPooling1D())
model.add(Dropout(0.5))
model.add(Flatten())
model.add(Dropout(0.5))
model.add(Dense(5, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
epochs = 100
batch_size = 32
history = model.fit(train_padded, training_labels, shuffle=True ,
epochs=epochs, batch_size=batch_size,
validation_split=0.2,
callbacks=[ReduceLROnPlateau(monitor='val_loss', factor=0.2, patience=3, min_lr=0.0001),
EarlyStopping(monitor='val_loss', mode='min', patience=3, verbose=1),
EarlyStopping(monitor='val_accuracy', mode='max', patience=3, verbose=1)])
I have an error:
ValueError: Shapes (None, 4) and (None, 5) are incompatible
Have you any idea please.
This is the original notebook: https://github.com/snymanje/MultiClass-Text-Classification-with-Tensorflow/blob/master/MultiClass_Text_Classification_with_Tensorflow.ipynb
When I added my database, I git this error when fitting the model.
Thank you
Looks like your labels don't tie to your model.
Try changing this line:
model.add(Dense(4, activation='softmax'))
Related
The following is my code:
The shape of my X_train is TensorShape([600, 22000, 5])
The shape of my Y_train is (600, 9)
Is there an error with the type of data that I am using for this time-series problem?
model = Sequential()
model.add(LSTM(256,return_sequences=True,input_shape=(22000, 5)))
model.add(Dense(9, activation='softmax'))
model.compile(optimizer='adam',loss='categorical_crossentropy', metrics=['accuracy'])
print(model.summary())
#print(model.summary())
model.fit(allfileswow[:600], features_a1[:600], epochs=100,verbose=0)
Hi just like #Djinn mentioned add a flatten layer to make everything 1-D
model = Sequential()
model.add(LSTM(256,return_sequences=True,input_shape=(22000, 5)))
model.add(Flatten())
model.add(Dense(9, activation='softmax'))
model.compile(optimizer='adam',loss='categorical_crossentropy', metrics=['accuracy'])
print(model.summary())
Try removing 'return_sequences=True' as you don't need full sequence as the output for the next layer.
Refer lstm
X_np_new.shape, y.shape
((50876, 2304), (50876, 9))
Code:
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Activation
from tensorflow.keras.optimizers import SGD
model = Sequential()
model.add(Dense(5000, activation='relu', input_dim=X_np_new.shape[1]))
model.add(Dropout(0.1))
model.add(Dense(600, activation='relu'))
model.add(Dropout(0.1))
model.add(Dense(X_np_new.shape[1], activation='sigmoid'))
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy',
optimizer=sgd)
model.fit(X_np_new, y, epochs=5, batch_size=2000)
preds = model.predict(X_np_new)
I get error:
ValueError: Shapes (None, 9) and (None, 2304) are incompatible
What went wrong here?
Replace
model.add(Dense(X_np_new.shape[1], activation='sigmoid'))
With
model.add(Dense(y.shape[1], activation='sigmoid'))
Explanation:
Putting X_np_new.shape[1] in the last layer means you have 2304 classes because X_np_new.shape[1]=2304 but you actually have 9 classes that you can get that from y.shape[1].
ValueError: Shapes (None, 9) and (None, 2304) are incompatible
means that your model is expecting labels of Size [*, 2304] but your labels size is [*, 9].
I am working on an image classification problem where I have to deal with input images of 19 channels. I was successful in doing it with normal 3 channel or greyscale images but I am getting the following error when I changed my code and model to be trained upon 19 channeled inputs.
could not broadcast input array from shape (19,761,3) into shape (19,761,1227,3)
This is my code
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D
from keras.layers import Activation, Dropout, Flatten, Dense
from keras import backend as K
# dimensions of our images.
img_width, img_height = 761, 1227
train_data_dir = '/home/spectrograms/train'
validation_data_dir = '/home/spectrograms/test'
nb_train_samples = 814
nb_validation_samples = 134
epochs = 50
batch_size = 32
if K.image_data_format() == 'channels_first':
input_shape = (19, img_width, img_height)
else:
input_shape = (img_width, img_height,19)
model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3), input_shape=(19, img_width, img_height), border_mode='same'))
model.add(Activation('relu'))
model.add(Conv2D(32, kernel_size=(3, 3), border_mode='same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(3, 3), border_mode='same'))
model.add(Dropout(0.25))
model.add(Conv2D(64, kernel_size=(3, 3), border_mode='same'))
model.add(Activation('relu'))
model.add(Conv2D(64, kernel_size=(3, 3), border_mode='same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(3, 3), border_mode='same'))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(32, activation='relu'))
model.add(Dense(16, activation='relu'))
model.add(Dense(8, activation='relu'))
model.add(Dense(2, activation='softmax'))
model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy'])
model.summary()
# this is the augmentation configuration we will use for training
train_datagen = ImageDataGenerator(
rescale=1. / 255,
shear_range=0,
zoom_range=0,
horizontal_flip=False)
# this is the augmentation configuration we will use for testing:
# only rescaling
test_datagen = ImageDataGenerator(rescale=1. / 255)
train_generator = train_datagen.flow_from_directory(
train_data_dir,
target_size=(19,img_width, img_height),
batch_size=batch_size,
class_mode='binary')
validation_generator = test_datagen.flow_from_directory(
validation_data_dir,
target_size=(19,img_width, img_height),
batch_size=batch_size,
class_mode='binary')
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)
model.save_weights('/home/rahul/Roshan/CNN/Saved_models_13/custom/CNN_model.h5')
Here is my code:
model = Sequential()
model.add(Conv1D(32, kernel_size=3,
activation='relu',
input_shape=(14,1)))
model.add(MaxPooling1D(pool_size=1))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1, activation='softmax'))
model.summary()
model.compile(loss=keras.losses.categorical_crossentropy,
optimizer=keras.optimizers.Adadelta(),
metrics=['accuracy'])
model.fit(X_train.values, y_train.values,
batch_size=4,
epochs=1,
verbose=2,
validation_data=(X_test.values,y_test.values))
And error is:
Error when checking input: expected conv1d_35_input to have 3 dimensions, but got array with shape (13166, 14)
As suggested by other posts, I tweaked with flatten layer before output layer but that did not work.
My X_train.values.shape gives (13166, 14)
Any suggestion how should I fix this?
You need to reshape the X_train.values from (13166, 14) to (13166, 14, 1) as your input shape of CNN network is (None, 14, 1).
This may solve your problem:
X_train.values.reshape([-1,14,1])
I'm running a model using Keras and TensorFlow backend. Everything works perfect:
model = Sequential()
model.add(Dense(dim, input_dim=dim, activation='relu'))
model.add(Dense(200, activation='relu'))
model.add(Dense(1, activation='linear'))
model.compile(loss='mse', optimizer='Adam', metrics=['mae'])
history = model.fit(X, Y, epochs=12,
batch_size=100,
validation_split=0.2,
shuffle=True,
verbose=2)
But as soon as I include logger and callbacks so I can log for tensorboard, I get
InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor 'input_layer_input_2' with dtype float and shape [?,1329]...
Here's my code: (and actually, it worked 1 time, the very first time, then ecer since been getting that error)
model = Sequential()
model.add(Dense(dim, input_dim=dim, activation='relu'))
model.add(Dense(200, activation='relu'))
model.add(Dense(1, activation='linear'))
model.compile(loss='mse', optimizer='Adam', metrics=['mae'])
logger = keras.callbacks.TensorBoard(log_dir='/tf_logs',
write_graph=True,
histogram_freq=1)
history = model.fit(X, Y,
epochs=12,
batch_size=100,
validation_split=0.2,
shuffle=True,
verbose=2,
callbacks=[logger])
A tensorboard callback uses tf.summary.merge_all function in order to collect all tensors for histogram computations. Because of that - your summary is collecting tensors from previous models not cleared from previous model runs. In order to clear these previous models try:
from keras import backend as K
K.clear_session()
model = Sequential()
model.add(Dense(dim, input_dim=dim, activation='relu'))
model.add(Dense(200, activation='relu'))
model.add(Dense(1, activation='linear'))
model.compile(loss='mse', optimizer='Adam', metrics=['mae'])
logger = keras.callbacks.TensorBoard(log_dir='/tf_logs',
write_graph=True,
histogram_freq=1)
history = model.fit(X, Y,
epochs=12,
batch_size=100,
validation_split=0.2,
shuffle=True,
verbose=2,
callbacks=[logger])