train_generator = train_datagen.flow_from_directory(
train_dir,
target_size=(image_size, image_size),
batch_size=train_batchsize,
class_mode='categorical')
# Data Generator for Validation data
validation_generator = validation_datagen.flow_from_directory(
validation_dir,
target_size=(image_size, image_size),
batch_size=val_batchsize,
class_mode='categorical',
shuffle=False)
model = Sequential()
metrics_epoch = MetricsWithGenerator(validation_generator)
# Next, we declare the input layer: The input shape parameter should be the shape of 1 sample.
model.add(Conv2D(32, kernel_size=(3, 3),
activation='relu',
input_shape=[image_size, image_size, 3]))
# Add another layer
model.add(Conv2D(64, (3, 3), activation='relu'))
# MaxPooling2D is a way to reduce the number of parameters in our model by sliding a 2x2 pooling filter across the
# previous layer and taking the max of the 4 values in the 2x2 filter.
model.add(MaxPooling2D(pool_size=(2, 2)))
# Dropout layer we just added. This is a method for regularizing our model in order to prevent overfitting.
# Data Generator for Training data
train_generator = train_datagen.flow_from_directory(train_dir,
target_size=(image_size,
image_size),
batch_size=train_batchsize,
class_mode='binary')
# Data Generator for Validation data
validation_generator = validation_datagen.flow_from_directory(
validation_dir,
target_size=(image_size, image_size),
batch_size=val_batchsize,
class_mode='binary',
shuffle=False)
customMetrics = MetricsWithGenerator(validation_generator)
model = Sequential()
# Next, we declare the input layer: The input shape parameter should be the shape of 1 sample.
model.add(
Conv2D(32,
kernel_size=(3, 3),
activation='relu',
input_shape=[200, 200, 3]))
# Add another layer
model.add(Conv2D(64, (3, 3), activation='relu'))
# MaxPooling2D is a way to reduce the number of parameters in our model by sliding a 2x2 pooling filter across the
# previous layer and taking the max of the 4 values in the 2x2 filter.