import sys
import os

from keras.layers.pooling import MaxPool2D 

sys.path.append('c:/git/keras')
sys.path.append('c:/git/absl')

# installed 
# py -mpip install numpy
# py -mpip show numpy 
# py -mpip install tensorflow
# py -mpip show tensorflow
# py -mpip install matplotlib
# c:\users\skess\appdata\local\programs\python\python39\lib\site-packages

import tensorflow
import keras
from keras.optimizers import adam_v2
from tensorflow.keras.optimizers import Adam
from keras.datasets import cifar10
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.utils import np_utils
from keras.layers import Dense
from keras.layers import Activation
from keras.layers import Flatten
from keras.layers import Dropout
from keras.layers import BatchNormalization
from keras.layers import Conv2D
from keras.layers import MaxPooling2D
from keras.layers import AveragePooling2D
from keras.callbacks import EarlyStopping, ModelCheckpoint
from keras import regularizers
from keras import optimizers
from matplotlib import pyplot
from keras.callbacks import ModelCheckpoint
from keras.callbacks import LearningRateScheduler
from keras.preprocessing.image import load_img
from keras.preprocessing.image import img_to_array
from keras.preprocessing.image import array_to_img
from keras.optimizer_v2 import gradient_descent 

#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'

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
)

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=gradient_descent.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=[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()