import sys
import os

from keras.layers.pooling import MaxPool2D
from keras.optimizer_v2 import gradient_descent 

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 keras
from keras.models import Model
#from keras.optimizers import *
#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.callbacks import ModelCheckpoint
from tensorflow.keras.callbacks import ReduceLROnPlateau
from tensorflow.keras.callbacks import EarlyStopping
from keras import regularizers
from keras import optimizers
from matplotlib import pyplot
import numpy as np
import tensorflow
# from inception_module import *
from resnet50 import *
import math

# RESNET50 ARCHITECTIURE
image_size = (128, 128)

#model_weights_file='model_resnet50.hdf5'
model_name='resnet50.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=32,
    seed=50
)
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=32,
    seed=50
)

input_shape=(128,128,1)
epochs=200
#initial_lrate=0.01
initial_lrate=0.01
batch_size=128
#patience_on_early_stop=15
patience_on_early_stop=epochs*.10
#metric='val_mse'
#metric='val_loss'
#reduce_factor=.25
#reduce_factor=np.sqrt(0.1)
reduce_factor=9.9e-4
metric='val_loss'
mode='min'

#ReduceLROnPlateau
#reduce_lr=tensorflow.keras.callbacks.ReduceLROnPlateau(monitor=metric,factor=np.sqrt(0.1),patience=5,min_lr=0.5e-6,verbose=True)
#reduce_lr=tensorflow.keras.callbacks.ReduceLROnPlateau(monitor='val_mse',factor=reduce_factor,min_lr=0.5e-6,patience=5,verbose=True)
reduce_lr=tensorflow.keras.callbacks.ReduceLROnPlateau(monitor=metric,factor=reduce_factor,min_lr=0.1e-3,patience=5,verbose=True)

#Optimizer
optimizer=gradient_descent.SGD(learning_rate=initial_lrate, momentum=0.9, nesterov=False)
#optimizer=adam_v2.Adam(learning_rate=initial_lrate)

# Checkpointer
checkpointer=ModelCheckpoint(filepath=model_name,mode=mode,monitor=metric,verbose=1,save_best_only=True)

#Early Stopping
early_stopping=EarlyStopping(monitor=metric,mode=mode,verbose=1,patience=patience_on_early_stop)

# def resnet50(input_shape,classes)
model=resnet50(input_shape,1)
model.summary()
#model.compile(loss='binary_crossentropy',optimizer=optimizer,metrics=['accuracy','mse'])
model.compile(loss='binary_crossentropy',optimizer=optimizer,metrics=['accuracy'])
#history = model.fit(train_ds, validation_data=val_ds, epochs=epochs, batch_size=batch_size, callbacks=[reduce_lr,early_stopping,checkpointer])
history = model.fit(train_ds, validation_data=val_ds, epochs=epochs, batch_size=batch_size, callbacks=[early_stopping,checkpointer])
#model.save(model_name)

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