Input: A dataset of 800 images of cats and dogs
Output: import numpy as np
import keras
from keras.layers import Dense, Conv2D, MaxPooling2D, Dropout, Flatten
from keras.models import Sequential
from keras.preprocessing.image import ImageDataGenerator
# Create the neural network model
model = Sequential()
# Input layer
model.add(Conv2D(32, (3, 3), input_shape = (64, 64, 3), activation = ‘relu’))
# Hidden layers
model.add(MaxPooling2D(pool_size = (2, 2)))
model.add(Dropout(0.3))
model.add(Conv2D(64, (3, 3), activation = ‘relu’))
model.add(MaxPooling2D(pool_size = (2, 2)))
model.add(Dropout(0.3))
model.add(Conv2D(64, (3, 3), activation = ‘relu’))
model.add(MaxPooling2D(pool_size = (2, 2)))
model.add(Dropout(0.3))
# Output layer
model.add(Flatten())
model.add(Dense(units = 128, activation = ‘relu’))
model.add(Dense(units = 1, activation = ‘sigmoid’))
# Compile the model
model.compile(loss = ‘binary_crossentropy’, optimizer = ‘adam’, metrics = [‘accuracy’])
# Create data generator
datagen = ImageDataGenerator(rescale = 1./255, shear_range = 0.2, zoom_range = 0.2, horizontal_flip = True)
# Fit the model
train_generator = datagen.flow_from_directory(directory = ‘/path/to/dataset’, target_size = (64, 64), color_mode = ‘rgb’, class_mode = ‘binary’, batch_size = 32)
model.fit_generator(generator = train_generator, steps_per_epoch = 800, epochs = 5, validation_data = test_generator, validation_steps = 200)
Prompt: Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
Collate a machine learning model in Python that distinguishes between cats and dogs.
### Input:
A dataset of 800 images of cats and dogs
### Output:
import numpy as np
import keras
from keras.layers import Dense, Conv2D, MaxPooling2D, Dropout, Flatten
from keras.models import Sequential
from keras.preprocessing.image import ImageDataGenerator
# Create the neural network model
model = Sequential()
# Input layer
model.add(Conv2D(32, (3, 3), input_shape = (64, 64, 3), activation = ‘relu’))
# Hidden layers
model.add(MaxPooling2D(pool_size = (2, 2)))
model.add(Dropout(0.3))
model.add(Conv2D(64, (3, 3), activation = ‘relu’))
model.add(MaxPooling2D(pool_size = (2, 2)))
model.add(Dropout(0.3))
model.add(Conv2D(64, (3, 3), activation = ‘relu’))
model.add(MaxPooling2D(pool_size = (2, 2)))
model.add(Dropout(0.3))
# Output layer
model.add(Flatten())
model.add(Dense(units = 128, activation = ‘relu’))
model.add(Dense(units = 1, activation = ‘sigmoid’))
# Compile the model
model.compile(loss = ‘binary_crossentropy’, optimizer = ‘adam’, metrics = [‘accuracy’])
# Create data generator
datagen = ImageDataGenerator(rescale = 1./255, shear_range = 0.2, zoom_range = 0.2, horizontal_flip = True)
# Fit the model
train_generator = datagen.flow_from_directory(directory = ‘/path/to/dataset’, target_size = (64, 64), color_mode = ‘rgb’, class_mode = ‘binary’, batch_size = 32)
model.fit_generator(generator = train_generator, steps_per_epoch = 800, epochs = 5, validation_data = test_generator, validation_steps = 200)