DenseNet

from __future__ import print_function

import os.path

import densenet
import numpy as np
import sklearn.metrics as metrics

#from keras.datasets import cifar10
from keras.utils import np_utils
from keras.preprocessing.image import ImageDataGenerator
from keras.optimizers import Adam
from keras.callbacks import ModelCheckpoint, ReduceLROnPlateau
from keras import backend as K

batch_size = 8
nb_classes = 3
nb_epoch = 10


from keras.callbacks import TensorBoard
tbCallBack = TensorBoard(log_dir='./log', histogram_freq=1,
                         write_graph=True,
                         write_grads=True,
                         batch_size=batch_size,
                         write_images=True)

img_rows, img_cols = 240, 320
img_channels = 3

img_dim = (img_channels, img_rows, img_cols) if K.image_dim_ordering() == "th" else (img_rows, img_cols, img_channels)
depth = 40
nb_dense_block = 3
growth_rate = 12
nb_filter = -1
dropout_rate = 0.0 # 0.0 for data augmentation

model = densenet.DenseNet(img_dim, classes=nb_classes, depth=depth, nb_dense_block=nb_dense_block,
                          growth_rate=growth_rate, nb_filter=nb_filter, dropout_rate=dropout_rate, weights=None)
print("Model created")

model.summary()
optimizer = Adam(lr=1e-3) # Using Adam instead of SGD to speed up training
model.compile(loss='categorical_crossentropy', optimizer=optimizer, metrics=["accuracy"])
print("Finished compiling")
print("Building model...")



# Load model
weights_file="/content/gdrive/My Drive/PhD/weights/DenseNet-40-12.h5"
if os.path.exists(weights_file):
    #model.load_weights(weights_file, by_name=True)
    print("Model loaded.")

out_dir="/content/gdrive/My Drive/PhD/weights/"

lr_reducer      = ReduceLROnPlateau(monitor='val_acc', factor=np.sqrt(0.1),
                                    cooldown=0, patience=5, min_lr=1e-5)
model_checkpoint= ModelCheckpoint(weights_file, monitor="val_acc", save_best_only=True,
                                  save_weights_only=True, verbose=1)

callbacks=[lr_reducer, model_checkpoint]

my_training_batch_generator = My_Generator(TrainPaths, TrainLabels, batch_size)
my_validation_batch_generator = My_Generator(TestPaths, TestLabels, batch_size)



model.fit_generator(generator=my_training_batch_generator,
                    steps_per_epoch=len(TrainPaths) // batch_size, epochs=nb_epoch,
                    callbacks=callbacks,
                    validation_data=my_validation_batch_generator,
                    validation_steps=len(TestPaths) // batch_size,
                    verbose=1)