Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- import numpy as np
- from keras.layers import Dense, GlobalAveragePooling2D
- from keras.models import Sequential
- from keras.optimizers import Adam
- from tensorflow.keras.preprocessing.image import ImageDataGenerator
- from tensorflow.keras.applications import ResNet50
- def load_train(path):
- datagen = ImageDataGenerator(rescale=1/255)
- train_datagen_flow = datagen.flow_from_directory(
- path,
- target_size=(150, 150),
- class_mode='sparse',
- seed=12345)
- return train_datagen_flow
- def create_model(input_shape):
- backbone = ResNet50(input_shape=(150, 150, 3), weights='/datasets/keras_models/resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5', include_top=False)
- model = Sequential()
- model.add(backbone)
- model.add(GlobalAveragePooling2D())
- model.add(Dense(12, activation='softmax'))
- model.compile(optimizer=Adam(learning_rate=0.00001),
- loss='sparse_categorical_crossentropy',
- metrics=['acc'])
- return model
- def train_model(model, train_datagen_flow, test_data, batch_size=None, epochs=10, steps_per_epoch=None, validation_steps=None):
- model.fit(train_datagen_flow,
- validation_data=test_data,
- batch_size=batch_size, epochs=epochs,
- steps_per_epoch=steps_per_epoch,
- validation_steps=validation_steps,
- verbose=2)
- return model
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
