embedding_vecor_length = 32
model = Sequential()
model.add(
Embedding(max_features,
embeddings_dim,
input_length=max_sent_len,
mask_zero=False,
weights=[embedding_weights]))
model.add(Dropout(dropout_prob[1]))
model.add(LSTM(100))
model.add(Dropout(dropout_prob[1]))
if num_classes == 2:
model.add(Dense(1, activation='sigmoid'))
else:
model.ad(Dense(num_classes, activation='sigmoid'))
if num_classes == 2:
model.compile(loss='binary_crossentropy',
optimizer='Adagrad',
metrics=['accuracy'])
else:
model.compile(loss='categorical_crossentropy',
optimizer='Adagrad',
metrics=['accuracy'])
# model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
print(model.summary())
# plot_model(model, to_file='C:\\Users\\paperspace\\Desktop\\Plots\\model_plot.png', show_shapes=True, show_layer_names=True)
plot_model(
model,
to_file='C:\\Users\\paperspace\\Desktop\\Plots\\model_plot_LSTM_2.png',
#Initialising the CNN
classifier = Sequential()
#Step 1 - Convolution
classifier.add(
Convolution2D(32, 3, 3, input_shape(64, 64, 3), activation='relu'))
#Step 2 - Pooling
classifier.add(MaxPooling2D(pool_size=(2, 2)))
#Step 3 - Flattening
classifier.add(Flatten())
#Step 3 - Full Connection
classifier.ad(Dense(units=128, activation='relu'))
classifier.ad(Dense(units=1, activation='sigmoid'))
#Compiling the CNN
classifier.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy'])
#Part 2 - Fitting the CNN to the images
from keras.preprocessing.image import ImageDataGenerated
train_datagen = ImageDataGenerator(rescale=1. / 255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
test_datagen = ImageDataGenerator(rescale=1. / 255)
