#!/usr/bin/env python
# coding: utf-8

# # Exercise 7
# 
# Data Preparation

# We will train our network on the **CIFAR10** [dataset](https://www.cs.toronto.edu/~kriz/cifar.html), which contains `50,000` 32x32 color training images, labeled over 10 categories, and 10,000 test images. 
# 
# As this dataset is also included in Keras datasets, we just ask the `keras.datasets` module for the dataset.
# 
# Training and test images are normalized to lie in the $\left[0,1\right]$ interval.

# In[1]:


from keras.datasets import cifar10
from keras.utils import np_utils
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
get_ipython().run_line_magic('matplotlib', 'inline')


# In[2]:


# Normal option with full database
# (X_train, y_train), (X_test, y_test) = cifar10.load_data()  # File is 160MB


# In[3]:


# Only the first training batch and testing  # File is 58MB
import tarfile
from six.moves import cPickle

# Use local copy of the cifar-10 database
data_tar = tarfile.open('../datasets/cifar-10-python_trainingbatch1_test.tar.gz')

def extract_xy(member, data_tar):
    d = cPickle.load(data_tar.extractfile(member), encoding='bytes')
    d_decoded = {}
    for k, v in d.items():
        d_decoded[k.decode('utf8')] = v
    d = d_decoded
    X = d['data']
    X = X.reshape(X.shape[0], 3, 32, 32)
    y = d['labels']
    return X.transpose(0, 2, 3, 1), np.reshape(y, (len(y), 1))

X_train, y_train = extract_xy('cifar-10-batches-py/data_batch_1', data_tar)
X_test, y_test = extract_xy('cifar-10-batches-py/test_batch', data_tar)


# In[4]:


X_train.shape, X_test.shape


# In[5]:


nb_classes = y_train.max() + 1
Y_train = np_utils.to_categorical(y_train, nb_classes)
Y_test = np_utils.to_categorical(y_test, nb_classes)
X_train = X_train.astype("float32")
X_test = X_test.astype("float32")
X_train /= 255
X_test /= 255


# In[6]:


labels = ['airplane', 'automobile','bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship','truck']


# In[7]:


X_train[0].shape


# In[8]:


y_train[0]


# In[9]:


Y_train[0]


# In[10]:


# Select one image per y
images = [np.nonzero(Y_train[:,i] == 1)[0][0] for i in range(nb_classes)]

# Plot all images
fig, ax = plt.subplots(4,3, figsize=(10,10))
ax = ax.reshape(12)
for i in range(nb_classes):
    ax[i].imshow(X_train[images[i]])
    ax[i].set_title(labels[y_train[images[i]][0]])
    ax[i].axis('off')

ax[-1].axis('off')
ax[-2].axis('off')
plt.show()


# # Exercise 08.1
# 
# Train a Softmax regression using keras
# Optimized using rmsprop using as loss categorical_crossentropy
# 
# Hints: 
# - test with two iterations then try more. 
# - learning can be ajusted
# 
# Evaluate the performance using the testing set (aprox 31% with 50 epochs)

# In[11]:


from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Conv2D, MaxPooling2D
from livelossplot import PlotLossesKeras


# In[ ]:





# # Exercise 08.2
# 
# Train a Deep Neural Network with the following architecture:
# 
# - Input = Image (32, 32, 3)
# - Conv2d(32, (3,3), padding='same')
# - Relu Activation
# - MaxPooling2D (2,2)
# - Dropout(0.5)
# - Flattern
# - Dense(10, Softmax)
# 
# Optimized using rmsprop using as loss categorical_crossentropy
# 
# Hints: 
# - test with two iterations then try more. 
# - learning can be ajusted
# 
# Evaluate the performance using the testing set (aprox 55% with 50 epochs)

# In[ ]:





# # Exercise 08.3
# 
# Use the last layer of VGG16 as the input to a neural network with softmax output
# 
# - Input = Image (32, 32, 3)
# - VGG16 
# - Flattern
# - Dense(512, Softmax)
# - Dropout(0.5)
# - Dense(10, Softmax)
# 
# Optimized using rmsprop using as loss categorical_crossentropy
# 
# Hints: 
# - test with two iterations then try more. 
# - learning can be ajusted
# 
# Evaluate the performance using the testing set (aprox 57% with 50 epochs)

# In[20]:


from keras.applications.vgg16 import VGG16
model_vgg16 = VGG16(weights='imagenet', include_top=False)


# In[ ]:





# # Exercise *08.4 (Bonus)
# 
# Test a different pre-train algorithm (https://keras.io/applications/#usage-examples-for-image-classification-models) 

# In[ ]: