import keras
from keras.applications.vgg16 import VGG16, preprocess_input, decode_predictions
from keras.preprocessing import image
import requests
from skimage.segmentation import slic
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import shap
import warnings

%matplotlib inline

# make a color map
from matplotlib.colors import LinearSegmentedColormap
colors = []
for l in np.linspace(1, 0, 100):
    colors.append((245 / 255, 39 / 255, 87 / 255, l))
for l in np.linspace(0, 1, 100):
    colors.append((24 / 255, 196 / 255, 93 / 255, l))
cm = LinearSegmentedColormap.from_list("shap", colors)

# load model data
r = requests.get('https://s3.amazonaws.com/deep-learning-models/image-models/imagenet_class_index.json')
feature_names = r.json()
model = VGG16()

# load an image
file = "../images/apple-banana.jpg"
img = image.load_img(file, target_size=(224, 224))
img_orig = image.img_to_array(img)
plt.imshow(img);
plt.axis('off');

# Create segmentation to explain by segment, not every pixel
segments_slic = slic(img, n_segments=30, compactness=30, sigma=3)

plt.imshow(segments_slic);
plt.axis('off');

segments_slic

# define a function that depends on a binary mask representing if an image region is hidden
def mask_image(zs, segmentation, image, background=None):
    
    if background is None:
        background = image.mean((0, 1))
        
    # Create an empty 4D array
    out = np.zeros((zs.shape[0], 
                    image.shape[0], 
                    image.shape[1], 
                    image.shape[2]))
    
    for i in range(zs.shape[0]):
        out[i, :, :, :] = image
        for j in range(zs.shape[1]):
            if zs[i, j] == 0:
                out[i][segmentation == j, :] = background
    return out


def f(z):
    return model.predict(
        preprocess_input(mask_image(z, segments_slic, img_orig, 255)))

def fill_segmentation(values, segmentation):
    out = np.zeros(segmentation.shape)
    for i in range(len(values)):
        out[segmentation == i] = values[i]
    return out

masked_images = mask_image(np.zeros((1,50)), segments_slic, img_orig, 255)

plt.imshow(masked_images[0][:,:, 0]);
plt.axis('off');

# use Kernel SHAP to explain the network's predictions
explainer = shap.KernelExplainer(f, np.zeros((1,50)))

with warnings.catch_warnings():
    warnings.simplefilter("ignore")
    shap_values = explainer.shap_values(np.ones((1,50)), nsamples=100) # runs VGG16 1000 times

predictions = model.predict(preprocess_input(np.expand_dims(img_orig.copy(), axis=0)))
top_preds = np.argsort(-predictions)

pd.Series(data={feature_names[str(inds[i])][1]:predictions[0, inds[i]]  for i in range(10)}).plot(kind='bar', title='Top 10 Predictions');

# Visualize the explanations
fig, axes = plt.subplots(nrows=1, ncols=4, figsize=(12,4))
inds = top_preds[0]
axes[0].imshow(img)
axes[0].axis('off')

max_val = np.max([np.max(np.abs(shap_values[i][:,:-1])) for i in range(len(shap_values))])
for i in range(3):
    m = fill_segmentation(shap_values[inds[i]][0], segments_slic)
    axes[i+1].set_title(feature_names[str(inds[i])][1])
    axes[i+1].imshow(np.array(img.convert('LA'))[:, :, 0], alpha=0.15)
    im = axes[i+1].imshow(m, cmap=cm, vmin=-max_val, vmax=max_val)
    axes[i+1].axis('off')
cb = fig.colorbar(im, ax=axes.ravel().tolist(), label="SHAP value", orientation="horizontal", aspect=60)
cb.outline.set_visible(False)
plt.show()

import numpy as np
import matplotlib.pyplot as plt

img = np.random.randint(0, 255, (64, 64))
img

plt.imshow(img);
plt.axis('off');

plt.savefig('../images/savefig_sample_image.png')

!ls ../images | grep image.png

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline

# Dataset
from sklearn.datasets import load_digits

# PyTorch
import torch 
import torchvision
import torchvision.transforms as transforms

import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim

def imshow(img):
    img = img / 2 + 0.5 # unnormalize
    npimg = img.numpy()
    plt.imshow(np.transpose(npimg, (1, 2, 0)))
    plt.axis('off')
    plt.show()

transform = transforms.Compose(
    [transforms.ToTensor(),
     transforms.Normalize((0.5, ), (0.5, ))])

trainset = torchvision.datasets.MNIST(root='~/data', 
                                        train=True,
                                        download=True,
                                        transform=transform)

testset = torchvision.datasets.MNIST(root='~/data', 
                                        train=False, 
                                        download=True, 
                                        transform=transform)

trainloader = torch.utils.data.DataLoader(trainset,
                                          batch_size=100,
                                          shuffle=True,
                                          num_workers=2)

testloader = torch.utils.data.DataLoader(testset,
                                         batch_size=100,
                                         shuffle=False,
                                         num_workers=2)

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 32, 3)  # 28x28x32 -> 26x26x32
        self.conv2 = nn.Conv2d(32, 64, 3)  # 26x26x64 -> 24x24x64
        self.pool = nn.MaxPool2d(2, 2)  # 24x24x64 -> 12x12x64
        self.dropout1 = nn.Dropout2d()
        self.fc1 = nn.Linear(12 * 12 * 64, 128)
        self.dropout2 = nn.Dropout2d()
        self.fc2 = nn.Linear(128, 10)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        x = self.pool(F.relu(self.conv2(x)))
        x = self.dropout1(x)
        x = x.view(-1, 12 * 12 * 64)
        x = F.relu(self.fc1(x))
        x = self.dropout2(x)
        x = self.fc2(x)
        return x

model = Net()
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.001, momentum=0.9)

epochs = 5
for epoch in range(epochs):
    running_loss = 0.0
    for i, (inputs, labels) in enumerate(trainloader, 0):
        # zero the parameter gradients
        optimizer.zero_grad()

        # forward + backward + optimize
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        # print statistics
        running_loss += loss.item()
        if i % 100 == 99:
            print(f'[{epoch + 1}, {i+1}] loss: {running_loss / 100:.2}')
            running_loss = 0.0

print('Finished Training')

dataiter = iter(testloader)
images, labels = dataiter.next()
outputs = model(images)
_, predicted = torch.max(outputs, 1)

n_test = 10
df_result = pd.DataFrame({
    'Ground Truth': labels[:n_test],
    'Predicted label': predicted[:n_test]})
display(df_result.T)
imshow(torchvision.utils.make_grid(images[:n_test, :, :, :], nrow=n_test))

import pandas as pd
import copy

# Torch & Tensorflow
import torch
import torch.nn as nn
import torch.nn.functional as F
import torchvision
import tensorflow as tf

# Visualization
from torchviz import make_dot
from PIL import Image
import matplotlib.pyplot as plt
%matplotlib inline

import warnings

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# desired size of the output image
imsize = (512, 512) if torch.cuda.is_available() else (128, 128)  # use small size if no gpu

loader = torchvision.transforms.Compose([
    torchvision.transforms.Resize(imsize),  # scale imported image
    torchvision.transforms.ToTensor()])  # transform it into a torch tensor

def image_loader(image_name):
    image = Image.open(image_name)

    # fake batch dimension required to fit network's input dimensions
    image = loader(image).unsqueeze(0)
    return image.to(device, torch.float)

unloader = torchvision.transforms.ToPILImage() 

def imshow_tensor(tensor, ax=None):
    image = tensor.cpu().clone()  # we clone the tensor to not do changes on it
    image = image.squeeze(0)      # remove the fake batch dimension

    image = unloader(image)
    if ax:
        ax.imshow(image)
    else:
        plt.imshow(image)

class ContentLoss(nn.Module):

    def __init__(self, target,):
        super(ContentLoss, self).__init__()
        self.target = target.detach()

    def forward(self, input):
        self.loss = F.mse_loss(input, self.target)
        return input
    
def gram_matrix(input):
    # Get the size of tensor
    # a: batch size
    # b: number of feature maps
    # c, d: the dimension of a feature map
    a, b, c, d = input.size() 
    
    # Reshape the feature 
    features = input.view(a * b, c * d)

    # Multiplication
    G = torch.mm(features, features.t())  
    
    # Normalize 
    G_norm = G.div(a * b * c * d)
    return G_norm

class StyleLoss(nn.Module):

    def __init__(self, target_feature):
        super(StyleLoss, self).__init__()
        self.target = gram_matrix(target_feature).detach()

    def forward(self, input):
        G = gram_matrix(input)
        self.loss = F.mse_loss(G, self.target)
        return input

cnn_normalization_mean = torch.tensor([0.485, 0.456, 0.406]).to(device)
cnn_normalization_std = torch.tensor([0.229, 0.224, 0.225]).to(device)

# create a module to normalize input image so we can easily put it in a
# nn.Sequential
class Normalization(nn.Module):
    def __init__(self, mean, std):
        super(Normalization, self).__init__()
        # .view the mean and std to make them [C x 1 x 1] so that they can
        # directly work with image Tensor of shape [B x C x H x W].
        # B is batch size. C is number of channels. H is height and W is width.
        self.mean = torch.tensor(mean).view(-1, 1, 1)
        self.std = torch.tensor(std).view(-1, 1, 1)

    def forward(self, img):
        # normalize img
        return (img - self.mean) / self.std

# desired depth layers to compute style/content losses :
content_layers_default = ['conv_4']
style_layers_default = ['conv_1', 'conv_2', 'conv_3', 'conv_4', 'conv_5']

def get_style_model_and_losses(cnn, normalization_mean, normalization_std,
                               style_img, content_img,
                               content_layers=content_layers_default,
                               style_layers=style_layers_default):
    cnn = copy.deepcopy(cnn)

    # normalization module
    normalization = Normalization(normalization_mean, normalization_std).to(device)

    # just in order to have an iterable access to or list of content/syle
    # losses
    content_losses = []
    style_losses = []

    # assuming that cnn is a nn.Sequential, so we make a new nn.Sequential
    # to put in modules that are supposed to be activated sequentially
    model = nn.Sequential(normalization)

    i = 0  # increment every time we see a conv
    for n_child, layer in enumerate(cnn.children()):
#         print()
#         print(f"n_child: {n_child}")
        if isinstance(layer, nn.Conv2d):
            i += 1
            name = 'conv_{}'.format(i)
        elif isinstance(layer, nn.ReLU):
            name = 'relu_{}'.format(i)
            # The in-place version doesn't play very nicely with the ContentLoss
            # and StyleLoss we insert below. So we replace with out-of-place
            # ones here.
            layer = nn.ReLU(inplace=False)
        elif isinstance(layer, nn.MaxPool2d):
            name = 'pool_{}'.format(i)
        elif isinstance(layer, nn.BatchNorm2d):
            name = 'bn_{}'.format(i)
        else:
            raise RuntimeError('Unrecognized layer: {}'.format(layer.__class__.__name__))

        model.add_module(name, layer)
#         print(f'Name: {name}')
        if name in content_layers:
#             print(f'Add content loss {i}')
            # add content loss:
            target = model(content_img).detach()
            content_loss = ContentLoss(target)
            model.add_module("content_loss_{}".format(i), content_loss)
            content_losses.append(content_loss)

        if name in style_layers:
#             print(f'Add style loss {i}')
            # add style loss:
            target_feature = model(style_img).detach()
            style_loss = StyleLoss(target_feature)
            model.add_module("style_loss_{}".format(i), style_loss)
            style_losses.append(style_loss)

    # now we trim off the layers after the last content and style losses
    for i in range(len(model) - 1, -1, -1):
        if isinstance(model[i], ContentLoss) or isinstance(model[i], StyleLoss):
            break

    model = model[:(i + 1)]

    return model, style_losses, content_losses

d_path = {}
d_path['content'] = tf.keras.utils.get_file('turtle.jpg','https://storage.googleapis.com/download.tensorflow.org/example_images/Green_Sea_Turtle_grazing_seagrass.jpg')
d_path['style'] = tf.keras.utils.get_file('kandinsky.jpg','https://storage.googleapis.com/download.tensorflow.org/example_images/Vassily_Kandinsky%2C_1913_-_Composition_7.jpg')

style_img = image_loader(d_path['style'])[:, :, :, :170]
content_img = image_loader(d_path['content'])[:, :, :, :170]
input_img = content_img.clone()

assert style_img.size() == content_img.size(), \
    "we need to import style and content images of the same size"

# Obtain the model for style transfer
# with warnings.catch_warnings():
warnings.filterwarnings("ignore")
cnn = torchvision.models.vgg19(pretrained=True).features.to(device).eval()
model, style_losses, content_losses = get_style_model_and_losses(cnn, cnn_normalization_mean, cnn_normalization_std, style_img, content_img)

def get_input_optimizer(input_img):
    # this line to show that input is a parameter that requires a gradient
    optimizer = torch.optim.LBFGS([input_img.requires_grad_()])
    return optimizer

optimizer = get_input_optimizer(input_img)

# Parameters
num_steps = 10
style_weight=5000
content_weight=1
input_img = content_img[:, :, :, :170].clone()
d_images = {}

print('Building the style transfer model..')
model, style_losses, content_losses = get_style_model_and_losses(cnn,
    cnn_normalization_mean, cnn_normalization_std, style_img, content_img)
optimizer = get_input_optimizer(input_img)

# Execution
run = [0]
while run[0] <= num_steps:

    def closure():
        # correct the values of updated input image
        input_img.data.clamp_(0, 1)

        optimizer.zero_grad()
        model(input_img)
        style_score = 0
        content_score = 0

        for sl in style_losses:
            style_score += sl.loss
        for cl in content_losses:
            content_score += cl.loss

        style_score *= style_weight
        content_score *= content_weight

        loss = style_score + content_score
        loss.backward()

        run[0] += 1
        if run[0] % 2 == 0:
            print("run {}:".format(run))
            print('Style Loss : {:4f} Content Loss: {:4f}'.format(
                style_score.item(), content_score.item()))
            input_img.data.clamp_(0, 1)
            d_images[run[0]] = input_img
            print()

        return style_score + content_score

    optimizer.step(closure)

    # a last correction...
    input_img.data.clamp_(0, 1)

fig, axes = plt.subplots(1, 3, figsize=(16, 8))
d_img = {"Content": content_img,
         "Style": style_img,
         "Output": input_img}
for i, key in enumerate(d_img.keys()):
    imshow_tensor(d_img[key], ax=axes[i])
    axes[i].set_title(f"{key} Image")
    axes[i].axis('off')

fig, axes = plt.subplots(int(len(d_images)/2), 2, figsize=(16, 20))
for i, key in enumerate(d_images.keys()):
    imshow_tensor(d_images[key], ax=axes[i//2][i%2])
    axes[i//2][i%2].set_title("run {}:".format(key))
    axes[i//2][i%2].axis('off')

import pandas as pd

# Torch & Tensorflow
import torch
import torch.nn as nn
import torch.nn.functional as F
import tensorflow as tf

# Visualization
from PIL import Image
import matplotlib.pyplot as plt
%matplotlib inline