import sys
import os

from keras.optimizers import SGD
from keras.optimizers import Adam
from tensorflow.keras.callbacks import TensorBoard
import keras
from keras.src.legacy.preprocessing.image import ImageDataGenerator
from keras.callbacks import ModelCheckpoint
from tensorflow.keras.callbacks import EarlyStopping
from keras.layers import Flatten
from keras.layers import Dense
from keras.layers import MaxPool2D
from keras.layers import Dropout
from keras.models import Model
from keras.layers import AveragePooling2D
from keras.models import Sequential
import numpy as np
import tensorflow
from inception_module import *
import math
from time import time

#Load some data
#(x_train,y_train), (x_test,y_test)=cifar10.load_data()

base_filters=6
image_size = (128, 128)
batch_size = 256
learning_rate=.00001
epochs=1000
patience_on_early_stop=10
model_name='lenet5.h5.keras'

train_ds = tensorflow.keras.preprocessing.image_dataset_from_directory(
    'C:\\boneyard\\DeepLearning\\data',
    label_mode="binary", 
    subset="training",
    validation_split=.20,   
    image_size=image_size,
    color_mode='grayscale',
    batch_size=64,
    seed=1337
)
val_ds = tensorflow.keras.preprocessing.image_dataset_from_directory(
    'C:\\boneyard\\DeepLearning\\data',
    label_mode="binary",   
    subset="validation",
    validation_split=.20,          
    image_size=image_size,
    color_mode='grayscale',
    batch_size=64,
    seed=1337
)

# Create a TensorBoard instance with the path to the logs directory.  Before training, in Terminal, run tensorboard --logdir=logs/
tensorboard = TensorBoard(log_dir='logs/{}'.format(time()))

model=Sequential()

#C1
model.add(Conv2D(filters=base_filters,kernel_size=(3,3),strides=1,activation='relu',input_shape=(128,128,1),padding='same'))
model.add(AveragePooling2D(pool_size=(2,2),strides=(2,2),padding='valid'))
model.add(BatchNormalization())

#C2
model.add(Conv2D(filters=base_filters*8,kernel_size=(3,3),strides=1,activation='relu',padding='valid'))
model.add(AveragePooling2D(pool_size=(2,2),strides=(2,2),padding='valid'))
model.add(Dropout(.20))

#C3 
model.add(Conv2D(filters=base_filters*16,kernel_size=(3,3),strides=1,activation='relu',padding='valid'))
model.add(BatchNormalization())

#C4 
model.add(Flatten())

#FC6
model.add(Dense(units=84,activation='relu'))

#FC7
model.add(Dense(units=1,activation='sigmoid'))

model.summary()

optimizer=SGD(learning_rate=learning_rate, momentum=0.9, nesterov=False)

checkpointer=ModelCheckpoint(filepath=model_name,monitor='accuracy',verbose=1,save_best_only=True)

early_stopping=EarlyStopping(monitor='val_loss',mode='min',verbose=1,patience=patience_on_early_stop)

model.compile(loss='binary_crossentropy',optimizer=optimizer,metrics=['accuracy'])

history=model.fit(train_ds, epochs=epochs, validation_data=val_ds,callbacks=[tensorboard,checkpointer,early_stopping])

# plot the learning curves
# pyplot.plot(history.history['accuracy'],label='train')
# pyplot.plot(history.history['val_accuracy'],label='validation')
# pyplot.legend()
# pyplot.show()