import cv2
import numpy as np
import os
from random import shuffle
from tqdm import tqdm
import tensorflow as tf
import tflearn
import itertools
from tflearn.layers.conv import conv_2d, max_pool_2d
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.estimator import regression

TRAIN_DIR = '/Users/xyz/Desktop/train'
TEST_DIR = '/Users/xyz/Desktop/test'
IMG_SIZE = 50
LR = 1e-3

MODEL_NAME = 'abcvsdef-{}-{}.model'.format(LR, '2conv-basic') # just so we remember which saved model is which, sizes must match

def label_img(img):
    word_label = img.split('.')[-3]
    # conversion to one-hot array [cat,dog]
    if word_label == 'm':
        return [1,0]
    elif word_label == 'n':
        return [0,1]

# process the training imnages and their labels into arrays

def create_train_data():
    training_data = []
    #for img in tqdm(os.listdir(TRAIN_DIR)):
    for root, dirs, files in os.walk(TRAIN_DIR):
        for file1, file2 in itertools.izip_longest(files[::2], files[1::2]):
            img1 = cv2.imread(root + '/' + file1)
            img2 = cv2.imread(root + '/' + file2)
            img1 = cv2.resize(img1,(IMG_SIZE,IMG_SIZE))
            img2 = cv2.resize(img2,(IMG_SIZE,IMG_SIZE))
            image_pairs = np.concatenate((img1, img2), axis=1)
            label = label_img(file1)
            training_data.append([np.array(image_pairs),np.array(label)])

    return training_data

# train the data
train_data = create_train_data()

# construct the CNN
convnet = input_data(shape=[None, IMG_SIZE, IMG_SIZE, 1], name='input')

convnet = conv_2d(convnet, 32, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)

convnet = conv_2d(convnet, 64, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)

convnet = conv_2d(convnet, 128, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)

convnet = conv_2d(convnet, 64, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)

convnet = conv_2d(convnet, 32, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)

convnet = fully_connected(convnet, 1024, activation='relu')
convnet = dropout(convnet, 0.8)

convnet = fully_connected(convnet, 2, activation='softmax')
convnet = regression(convnet, optimizer='adam', learning_rate=LR, loss='categorical_crossentropy', name='targets')

model = tflearn.DNN(convnet, tensorboard_dir='log')

train = train_data[:4]
test = train_data[4:]

X = np.array([i[0] for i in train]).reshape(-1,IMG_SIZE,IMG_SIZE,1)
Y = [i[1] for i in train]

test_x = np.array([i[0] for i in test]).reshape(-1,IMG_SIZE,IMG_SIZE,1)
test_y = [i[1] for i in test]

model.fit({'input': X}, {'targets': Y}, n_epoch=10, validation_set=({'input': test_x}, {'targets': test_y}),
    snapshot_step=500, show_metric=True, run_id=MODEL_NAME)

model.save(MODEL_NAME)

---------------------------------
Run id: abcvsdef-0.001-2conv-basic.model
Log directory: log/
---------------------------------
Training samples: 24
Validation samples: 24
--
Exception in thread Thread-3:
Traceback (most recent call last):
  File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/threading.py", line 810, in __bootstrap_inner
    self.run()
  File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/threading.py", line 763, in run
    self.__target(*self.__args, **self.__kwargs)
  File "/Library/Python/2.7/site-packages/tflearn/data_flow.py", line 187, in fill_feed_dict_queue
    data = self.retrieve_data(batch_ids)
  File "/Library/Python/2.7/site-packages/tflearn/data_flow.py", line 222, in retrieve_data
    utils.slice_array(self.feed_dict[key], batch_ids)
  File "/Library/Python/2.7/site-packages/tflearn/utils.py", line 187, in slice_array
    return X[start]
IndexError: index 19 is out of bounds for axis 0 with size 4